Self-Supervised Pre-Training

Ask about this topic

Overview

Self-supervised pre-training studies how models can learn useful structure from unlabeled data, making it possible to adapt them to new tasks with fewer annotations. Common approaches include masked autoencoders, contrastive learning, teacher-student distillation, and joint-embedding predictive architectures such as JEPA, applied to images, signals, video, text, and scientific data. Researchers test these representations through frozen-feature probes, fine-tuning, and few-label or cross-domain transfer on benchmarks in areas such as medical imaging, speech, and autonomous driving. Results show that pre-training can improve data efficiency and robustness, but its benefits depend on the match between objective, data, and downstream task; greater model size or training time does not reliably help.

Latest papers

CardsList

251 papers34 papers in the last four weeks, level with the four weeks before. 0.2% of all new papers.

May 7, 2026

TinySSL: Distilled Self-Supervised Pretraining for Sub-Megabyte MCU Models

Self-supervised learning (SSL) has transformed representation learning for large models, yet remains unexplored for microcontroller (MCU)-class models with fewer than 500K parameters. We identify three obstacles at this scale -- projection head dominance, representation bottleneck, and augmentation sensitivity -- and propose Capacity-Aware Distilled Self-Supervised Learning (CA-DSSL), a teacher-guided framework that overcomes them without labels or text supervision. CA-DSSL combines asymmetric distillation from a frozen DINO ViT-S/16 teacher, multi-scale feature distillation for spatial representations, and a progressive augmentation curriculum. On a MobileNetV2-0.35 backbone (396K parameters) pretrained on CIFAR-100, CA-DSSL reaches 62.7 0.5% linear-probe accuracy (3-seed mean) -- surpassing SimCLR-Tiny by 18 pp, matching SEED (61.7%) with 10 fewer projection parameters (426K vs. 3.15M), and reaching 94.0% of a supervised upper bound. Standard SSL methods (BYOL-Tiny, DINO-Tiny) collapse entirely at this scale. On Pascal VOC detection, CA-DSSL achieves 2.3 the mAP of random initialization and +3 pp over SEED, though SimCLR-Tiny matches CA-DSSL on detection mAP. The deployed backbone occupies 378 KB (INT8) with no inference overhead from pretraining. Preliminary ImageNet-100 experiments reveal that CA-DSSL's advantage is specific to small-data regimes; scaling to ImageNet-1K is discussed as future work.

Bibin Wilson

Self-Supervised LearningSelf-Supervised Pre-TrainingTiny MLKnowledge DistillationSelf-Supervised Visual Representation Learning
AskPDF
May 6, 2026

Attention-Based Chaotic Self-Supervision for Medical Image Classification

Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful alternative, yet common methods like masked autoencoders (MAEs) may inadvertently destroy fine-grained diagnostic features by using random masking. In this paper, we propose a novel SSL pre-training strategy, the Chaotic Denoising Autoencoder (CDAE). Instead of masking, we apply a chaotic transformation to the input image, tasking an autoencoder to reconstruct the original. We hypothesize this forces the encoder to learn robust, domain-specific features by "inverting the chaos". Furthermore, we propose an attentive fusion mechanism that combines features from our CDAE-trained encoder with a standard encoder, leveraging the strengths of both general and domain-specific representations. Our method is evaluated on two public medical datasets: ISIC 2018 (skin lesions) and APTOS 2019 (diabetic retinopathy). The proposed model achieves high performance, with an accuracy of 0.9221 and an F1-macro of 0.8530 on ISIC 2018, and an accuracy of 0.8644 and F1-macro of 0.7433 on APTOS 2019, demonstrating the efficacy of our approach.

Joao Batista Florindo, Amanda Pontes de Oliveira Ornelas

Institute of Mathematics, Statistics and Scientific Computing - University of Campinas, Rua S´ergio Buarque de Holanda, 651, Campinas, Brasil

Denoising AutoencodersSelf-Supervised Pre-TrainingAutoencodersMedical Image ClassificationMedical Image Representation Learning
AskPDF
May 5, 2026

Diffusion Masked Pretraining for Dynamic Point Cloud

Dynamic point cloud pretraining is still dominated by masked reconstruction objectives. However, these objectives inherit two key limitations. Existing methods inject ground-truth tube centers as decoder positional embeddings, causing spatio-temporal positional leakage. Moreover, they supervise inter-frame motion with deterministic proxy targets that systematically discard distributional structure by collapsing multimodal trajectory uncertainty into conditional means. To address these limitations, we propose Diffusion Masked Pretraining (DiMP), a unified self-supervised framework for dynamic point clouds. DiMP introduces diffusion modeling into both positional inference and motion learning. It first applies forward diffusion noise only to masked tube centers, then predicts clean centers from visible spatio-temporal context. This removes positional leakage while preserving visible coordinates as clean temporal anchors. DiMP also reformulates point-wise inter-frame displacement supervision as a DDPM noise-prediction objective conditioned on decoded representations. This design drives the encoder to target the full conditional distribution of plausible motions under a variational surrogate, rather than collapsing to a single deterministic estimate. Extensive experiments demonstrate that DiMP consistently improves downstream accuracy over the backbone alone, with absolute gains of 11.21% on offline action segmentation and 13.65% under causally constrained online inference.Codes are available at https://github.com/InitalZ/DiMP.git.

Zhuoyue Zhang, Yiding Sun, Haozhe Cheng +4

School of Software Engineering, Xi’an Jiaotong University, Xi’an, China · School of Artificial Intelligence and Robotics, Hunan University, Changsha, China · Department of Computer Science and Software Engineering, University of Western Australia, Perth, Australia

Self-Supervised Pre-TrainingPoint Cloud LearningPoint Cloud UnderstandingDiffusion ModelsSelf-Supervised Point Cloud Learning
AskPDF
May 3, 2026

SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition

Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-grained cues. We propose a self-supervised pretraining method for sign language recognition that uses segmentation-based masking to adapt to the presence and motion of key body parts, rather than treating hand poses as static visual tokens. The resulting mask-and-reconstruct objective improves fine-grained sign representation learning. On WLASL, NMFs-CSL, and Slovo, our encoder achieves state-of-the-art performance, improving per-instance and per-class Top-1 accuracy while using fewer input frames and modalities than comparable encoders.

Kunyuan Xie, Zhixi Cai, Kalin Stefanov

Monash University, Australia

Self-Supervised Pre-TrainingSign Language RecognitionSelf-Supervised Visual Representation Learning
AskPDF
May 3, 2026

PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning

Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Despite the advances in the field through existing methods, the sample-independent modeling paradigm still poses significant limitations in terms of maintaining consistent semantic representations across scenes. This challenge hinders the construction of a unified and transferable semantic space. To address this issue, we propose a PC-SSL framework based on cross-sample semantic propagation (CSP), in which samples within a batch are serialized into continuous input and processed by a state-space model to enable semantic state propagation. This mechanism explicitly models the dynamic dependencies across samples in the state space, allowing the network to establish cross-sample semantic consistency in the latent space and achieve global semantic alignment. Since serialization-based pretraining requires batch-level input organization, we further introduce an asymmetric semantic preservation distillation (SPD) during finetuning to achieve structural alignment of semantic transfer and eliminate inconsistencies caused by batch dependency. The proposed SPD ensures stable transfer of pretrained semantics through a heterogeneous input mechanism and a semantic feature alignment constraint. This enables the model to maintain structured semantic consistency and robustness under single-scene testing conditions. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art methods in both performance and semantic consistency.

Xinxing Yu, Ajian Liu, Sunyuan Qiang +5

Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China · MAIS, The Institute of Automation of the Chinese Academy of Sciences, Beijing, China · Southwest Institute of Technical Physics, Chengdu, China +1

Self-Supervised Point Cloud LearningSelf-Supervised Pre-TrainingPoint Cloud Learning3D Representation Learning
AskPDF
May 3, 2026

Adaptive Texture-aware Masking for Self-Supervised Learning in 3D Dental CBCT Analysis

Cone Beam Computed Tomography (CBCT) is pivotal for 3D diagnostic imaging in dentistry. However, the development of robust AI models for volumetric analysis is often constrained by the scarcity of large, annotated datasets. Self-supervised learning (SSL), particularly Masked Image Modeling (MIM), offers a promising pathway to leverage unlabeled data. A limitation of standard MIM is its reliance on random masking, which fails to prioritize diagnostically critical regions in dental CBCT volumes, such as subtle pathological changes and intricate anatomical boundaries. To address this, we propose ATMask, a novel adaptive masking strategy. Instead of applying random masks or employing computationally intensive attention modules, ATMask computes an inter-slice texture variation map to identify regions with high structural or textural complexity. These high-variation areas are then selectively masked during pre-training, compelling the model to learn richer contextual representations essential for inferring complex 3D morphological transitions. Furthermore, we contribute the first large-scale CBCT dataset, curated from both public and private sources, comprising 6,314 scans, for the dental AI model pretraining. Extensive experiments on three downstream dental CBCT tasks demonstrate that our ATMask enables more data-efficient and powerful representation learning than standard random masking and other advanced SSL baselines. The dataset and code will be released.

Xinquan Yang, Jianfeng Ren, Xuguang Li +4

School of Artificial Intelligence, Shenzhen University, Shenzhen, China. · School of Computer Science, University of Notting-ham Ningbo China, Ningbo, China. · Department of Stomatology, Shenzhen University General Hospital, Shenzhen, China.

Cone-Beam CTSelf-Supervised Pre-Training3D Representation LearningMasked Image Modeling
AskPDF
May 2, 2026

GraphSculptor: Sculpting Pre-training Coreset for Graph Self-supervised Learning

Graph self-supervised learning typically relies on large-scale unlabeled datasets, heavily inflating computational costs. However, empirical evidence suggests that these datasets contain substantial redundancy-our analysis reveals that uniformly subsampling 50% of graphs retains over 96% of downstream performance. To exploit this redundancy, we introduce GraphSculptor for pre-training coreset construction. Unlike methods dependent on additional training-time signals or limited solely to topological statistics, GraphSculptor provides a label-free solution that constructs coresets via two complementary perspectives: intrinsic structure and contextual semantics. Concretely, structural diversity is quantified using intrinsic graph statistics, yielding a structural feature vector for each graph, while semantic diversity is captured by utilizing a pre-trained language model to encode descriptions generated via graph-to-text. GraphSculptor integrates these signals into a unified metric space and performs cluster-aware selection to preserve joint structural-semantic diversity. We further derive a theoretical bound on the loss gap between coreset and full-data pre-training, offering theoretical motivation for our selection formulation. Extensive experiments demonstrate that GraphSculptor effectively sculpts the dataset: a 10% coreset achieves 99.6% of full-data performance while reducing pre-training time by nearly 90%, offering a scalable solution for data-efficient graph pre-training.

Chuang Liu, Zelin Yao, Xueqi Ma +4

Sangfor Technologies Inc. · Wuhan University · The University of Melbourne +2

Graph Representation LearningSelf-Supervised Pre-TrainingGraph SSLCoreset SelectionData-Efficient Learning
AskPDF
May 2, 2026

Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI

Self-supervised pretraining is promising for large-scale neuroimaging, yet the impact of region-aware masking and hybrid sequence modeling remains underexplored. In this work, we introduce Rhamba, a region-aware pretraining framework that integrates anatomically guided masking with hybrid Attention-Mamba architectures for resting state functional magnetic resonance imaging (fMRI) analysis. Models were pretrained on the ABIDE dataset using region-aligned patch embeddings and three masking strategies (Any, Majority, and Pure) with increasing spatial specificity. We evaluated four architectural variants: a Mamba only model, an Alternate architecture with interleaved Mamba and Attention blocks, and two hybrid encoder-decoder configurations (Attention-Mamba (AM) and Mamba-Attention (MA)). The pretrained models were fine-tuned on downstream classification tasks using the COBRE and ADHD-200 datasets for schizophrenia and attention-deficit/hyperactivity disorder discrimination. We employed Integrated Gradients, an explainable AI method, to identify the brain regions contributing to model predictions. Masking strategy strongly influenced reconstruction behavior, with reconstruction loss following a consistent ordering (Any > Majority > Pure). However, this trend did not directly translate into downstream performance, where differences were modest and dataset-dependent. The hybrid architecture with the MA configuration achieved the highest average AUROC across both datasets, and Rhamba outperformed state-of-the-art methods in comparative evaluation. Region-wise analysis showed that peak performance depends on the interaction between masking strategy and architecture rather than a single dominant configuration. Overall, Rhamba offers a flexible framework for balancing interpretability, scalability, and performance in large-scale fMRI representation learning.

Ruthwik Reddy Doodipala, Pankaj Pandey, Pratheek Eranki +3

1St. Jude Children’s Research Hospital · 2The University of Memphis

Self-Supervised Pre-TrainingSelf-Supervised Time Series Representation LearningNeuroimagingState Space ModelsMasked Image Modeling
AskPDF
Apr 30, 2026

UniBCI: Towards a Unified Pretrained Model for Invasive Brain-Computer Interfaces

Modeling invasive neural spike data is fundamental to advancing high-performance brain-computer interfaces (BCIs). However, existing approaches face critical challenges, including limited-scale heterogeneous data, cross-domain distribution shift, and the intrinsic spatiotemporal complexity of invasive neural signals. In this work, we propose UniBCI, a unified pretrained model for invasive Brain-Computer Interfaces. The model integrates three key components: (1) a context-conditioned spatio-temporal tokenization (CST) scheme that embeds neural signals together with metadata into a shared representation space; (2) a hierarchical Interval-Area Attention (IAA) mechanism that captures patterns of spike dynamics in slots via linear attention and locality dependencies via sliding-window attention; and (3) a scalable self-supervised masked signals reconstruction objective for learning generalizable neural representations from large-scale unlabeled data. We construct a pretraining corpus spanning multiple species, subjects, brain regions, and behavioral experiment paradigms. These heterogeneous recordings are standardize via our proposed unified normalization and tokenization. Comprehensive experiments demonstrate that UniBCI achieves SOTA performance across diverse downstream tasks while improving generalization. Moreover, the model achieves a strong balance between accuracy and efficiency, with fewer trainable parameters and lower inference latency. These results suggest that UniBCI provides a practical step toward general-purpose neural foundation models, enabling robust, scalable, and transferable representation learning for invasive neural data. The code for this paper is available at: https://anonymous.4open.science/r/UniBCI-C805.

Binjie Hong, Rui Xiong, Liyuan Han +1

Brain Science Data Center · CEBSIT, Institute of Neuroscience

Brain-Computer InterfacesSelf-Supervised Pre-TrainingNeural DecodingSelf-Supervised Time Series Representation Learning
AskPDF
Apr 30, 2026

LA-Pose: Latent Action Pretraining Meets Pose Estimation

This paper revisits camera pose estimation through the lens of self-supervised pretraining, focusing on inverse-dynamics pretraining as a scalable alternative to the current trend of fully supervised training with 3D annotations. Concretely, we employ inverse- and forward-dynamics models to learn latent action representations, similar to Genie from large-scale driving videos. Our idea is simple yet effective. Existing methods use latent actions in their original capacity, that is, as action conditioning of world-models or as proxies of robot action parameters in policy networks. Our method, dubbed LA-Pose, repurposes the latent action features as inputs to a camera pose estimator, finetuned on a limited set of high-quality 3D annotations. This formulation enables accurate and generalizable pose prediction while maintaining feed-forward efficiency. Extensive experiments on driving benchmarks show that LA-Pose achieves competitive and even superior performance to state-of-the-art methods while using orders of magnitude less labeled data. Concretely, on the Waymo and PandaSet benchmarks, LA-Pose achieves over 10% higher pose accuracy than recent feed-forward methods. To our knowledge, this work is the first to demonstrate the power of inverse-dynamics self-supervised learning for pose estimation.

Zhengqing Wang, Saurabh Nair, Prajwal Chidananda +4

1Wayve · 2Simon Fraser University

Self-Supervised Pre-TrainingCamera Pose EstimationAutonomous Driving
AskPDF
Apr 30, 2026

BrainDINO: A Brain MRI Foundation Model for Generalizable Clinical Representation Learning

Brain MRI underpins a wide range of neuroscientific and clinical applications, yet most learning-based methods remain task-specific and require substantial labeled data. Here we show that a single self-supervised representation can generalize across heterogeneous brain MRI endpoints. We trained BrainDINO, a self-distilled foundation model, on approximately 6.6 million unlabeled axial slices from 20 datasets encompassing broad variation in population, disease, and acquisition setting. Using a frozen encoder with lightweight task heads, BrainDINO supported transfer across tumor segmentation, neurodegenerative and neurodevelopmental conditions classification, brain age estimation, post-stroke temporal prediction, molecular status prediction, MRI sequence classification, and survival modeling. Across tasks and supervision regimes, BrainDINO consistently equaled or exceeded natural-image and MRI-specific self-supervised baselines, with particularly strong advantages under label scarcity. Representation analyses further showed anatomically organized and pathology-sensitive feature structure in the absence of task-specific supervision. Our findings indicate that large-scale slice-wise self-supervised learning can yield a unified brain MRI representation that supports diverse neuroimaging tasks without volumetric pretraining or full-network fine-tuning, establishing a scalable foundation for robust and data-efficient brain imaging analysis. Code is available at https://github.com/mclwu22/BrainDINO

Yizhou Wu, Shansong Wang, Yuheng Li +5

Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, USA. · Department of Radiation and Cellular Oncology, The University of Chicago, Chicago, IL, USA. · Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, USA. +2

Medical Imaging Foundation ModelsSelf-Supervised Pre-TrainingMedical Image Representation LearningBrain MRI
AskPDF
Apr 27, 2026

CLLAP: Contrastive Learning-based LiDAR-Augmented Pretraining for Enhanced Radar-Camera Fusion

Accurate 3D object detection is critical for autonomous driving, necessitating reliable, cost-effective sensors capable of operating in adverse weather conditions. Camera and millimeter-wave radar fusion has emerged as a promising solution; however, these methods often rely on finely annotated radar data, which is scarce and labor-intensive to produce. To address this challenge, we present CLLAP, a Contrastive Learning-based LiDAR-Augmented Pretraining framework that enhances the performance of existing radar-camera fusion methods for 3D object detection. CLLAP leverages abundant LiDAR data to generate pseudo-radar data using the proposed L2R (LiDAR-to-Radar) Sampling method. Then, it incorporates this data into a novel dual-stage, dual-modality contrastive learning strategy, enabling effective self-supervised learning from paired pseudo-radar and image data. This approach facilitates effective pretraining of existing radar-camera fusion models in a plug-and-play manner, enhancing their feature extraction capabilities and improving detection accuracy and robustness. Experimental results using NuScenes and Lyft Level 5 datasets demonstrate significant performance improvements across three baseline models, highlighting CLLAP's effectiveness in advancing radar-camera fusion for autonomous driving applications.

Bingyi Liu, Chuanhui Zhu, Hongfei Xue +5

Wuhan University of Technology · University of North Carolina at Charlotte · The Hong Kong Polytechnic University +2

Camera-Radar FusionSelf-Supervised Pre-Training3D Object DetectionMultimodal Contrastive Learning
AskPDF
Apr 24, 2026

SS3D: End2End Self-Supervised 3D from Web Videos

We present SS3D, a web-scale SfM-based self-supervision pretraining pipeline for feed-forward 3D estimation from monocular video. Our model jointly predicts depth, ego-motion, and intrinsics in a single forward pass and is trained/evaluated as a coherent end-to-end 3D estimator. To stabilize joint learning, we use an intrinsics-first two-stage schedule and a unified single-checkpoint evaluation protocol. Scaling SfM self-supervision to unconstrained web video is challenging due to weak multi-view observability and strong corpus heterogeneity; we address these with a multi-view signal proxy (MVS) used for filtering and curriculum sampling, and with expert training distilled into a single student. Pretraining on YouTube-8M (~100M frames after filtering) yields strong cross-domain zero-shot transfer and improved fine-tuning performance over prior self-supervised baselines. We release the pretrained checkpoint and code.

Marwane Hariat, Gianni Franchi, David Filliat +1

U2IS, ENSTA – Institut Polytechnique de Paris, Palaiseau, France · Pôle Recherche, Agence Ministérielle pour l’IA de Défense, Palaiseau, France

Monocular Depth EstimationDepth EstimationCamera Pose EstimationSelf-Supervised Pre-TrainingStructure from MotionVideo Depth Estimation+1
AskPDF
Apr 24, 2026

A Nationwide Japanese Medical Claims Foundation Model: Balancing Model Scaling and Task-Specific Computational Efficiency

Clinical risk prediction using longitudinal medical data supports individualized care. Self-supervised foundation models have emerged as a promising approach for leveraging large-scale unlabeled healthcare records. In natural language processing, scaling laws suggest that larger models achieve predictably lower pretraining losses, supporting the foundation model paradigm. However, for structured medical data, characterized by a limited vocabulary and sparse observations, whether increasing model size consistently improves downstream predictions is unclear, as most studies evaluate only a single model scale. In this study, we evaluated the relationship between model scale and downstream task performance for structured medical foundation models. Using a random sample (2.3 million patients, 32 hospitals) from a nationwide 519-hospital Japanese claims database, we pretrained encoder-only Transformers at five scales (2.2M-101M parameters) for disease incidence and medication prediction. Downstream performance saturated at task-dependent thresholds: disease prediction benefited from larger models (32M-101M), whereas medication prediction saturated at 11M, reducing pretraining time by 178 h. Across all tasks, the best-performing model consistently outperformed a Light Gradient Boosting Machine baseline in the area under the precision-recall curve. These findings indicate that, unlike the monotonically decreasing pretraining loss, the optimal model size varied depending on task characteristics. This task-dependent saturation provides practical guidance for balancing predictive performance and computational cost in structured medical foundation models.

Nanae Aratake, Taisei Tosaki, Yuji Okamoto +5

1Graduate School of Medicine, Kyoto University, Kyoto, Japan. · 2Medical Data Vision Co., Ltd., Tokyo, Japan. · 3IQVIA Solutions Japan G.K., Tokyo, Japan. +1

Self-Supervised Pre-TrainingClinical Outcome PredictionScaling LawsLongitudinal EHR Modeling
AskPDF
Apr 23, 2026

Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning

Numerical reasoning over expert-domain tables often exhibits high in-domain accuracy but limited robustness to domain shift. Models trained with supervised fine-tuning (SFT) on specific datasets tend to rely on header-operation shortcuts rather than structural reasoning. We introduce TaNOS, a continual pre-training framework comprising three components: (i) header anonymization to reduce lexical memorization, (ii) operation sketches that provide minimal structural cues, and (iii) self-supervised pretraining that constructs correctness-guaranteed program-question pairs from given tables in a program-first manner. By decoupling domain semantics and numerical operation structure, TaNOS improves the transferability of numerical reasoning. Applied to an 8B instruction-tuned model, TaNOS achieves 80.13% execution accuracy on FinQA with only 10% train data, outperforming SFT baseline (73.97%) with full train data and proprietary models such as GPT-5, Gemini-2.5-Pro. Furthermore, in the domain-shift experiments, TaNOS displays nearly-negligible cross-domain gap (<2pp) when standard SFT shows over 10pp gap. These results suggest that structural guidance with operation sketches, header-agnostic representations, and correctness-guaranteed self-supervision can improve the robustness of numerical reasoning across diverse expert-domain tables.

Hanjun Cho, Gahyun Yoo, Hanseong Kim +1

Seoul National University · Soongsil University

Table QASelf-Supervised Pre-TrainingDomain GeneralizationProgram Synthesis
AskPDF
Apr 22, 2026

MAE-Based Self-Supervised Pretraining for Data-Efficient Medical Image Segmentation Using nnFormer

Transformer architectures, including nnFormer,have demonstrated promising results in volumetric medical image segmentation by being able to capture long-range spatial interactions. Although they have high performance, these models need large quantities of labeled training data and are also likely to overfit and become training unstable. This is a serious practical problem because it is not only time-consuming but also expensive to obtain medical images that are annotated by experts. Moreover, fully supervised traditional training pipelines do not take advantage of the available large amounts of unlabeled medical imaging data that can be easily obtained in the clinics. We have solved these drawbacks by advancing the efficiency of the nnFormer with a self-supervised pretraining framework, which is based on the Masked Autoencoders (MAE). In this method, the model is pretrained on unlabeled volumetric medical images to reconstruct randomly masked parts of the input. This allows the encoder to learn meaningful anatomical and structural representations . The encoder is then further fine-tuned on a labeled dataset on the downstream segmentation task. Conducted Experiment shows that the offered method leads to a higher segmentation performance on the count of Dice score, a quicker convergence rate on the course of the fine-tuning procedure, and a superior generalization on the basis of limited labeled data . These findings validate that self-supervised learning combined with transformer-based segmentation models is an appropriate approach to the problem of data shortage in medical image analysis.

R. M. Krishna Sureddi, T. Satyanarayana Murthy, Nomula Varsha Reddy +2

Information Technology, Chaitanya Bharathi Institute of Technology, Hyderabad, India

Self-Supervised Pre-TrainingMedical Image Segmentation3D Medical Image SegmentationMedical Image Representation Learning
AskPDF
Apr 22, 2026

Self-supervised pretraining for an iterative image size agnostic vision transformer

Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with image size. Consequently, foundational models like DINO are constrained to low-resolution processing. A recent foveal-inspired transformer achieves resolution agnosticism by iteratively processing a fixed-size context of multi-zoom patches. This model demonstrated promising results via supervised learning, utilizing a sequential, recurrent-like process without backpropagation through time. To unlock its potential as a foundational backbone, we introduce a novel sequential-to-global SSL framework based on DINO's self-distillation objective. Supported by an efficient integral-image patch extraction method, our approach enables large-scale pretraining for image-size agnostic vision encoders. We achieve competitive performance on ImageNet-1K and downstream classification tasks, maintaining a constant computational budget regardless of input resolution.

Nedyalko Prisadnikov, Danda Pani Paudel, Yuqian Fu +1

INSAIT, Sofia University "St. Kliment Ohridski", Bulgaria

Self-Supervised Pre-TrainingVision TransformerEfficient ViTsSelf-Supervised Visual Representation Learning
AskPDF
Apr 17, 2026

PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking

Intelligent fetal ultrasound (US) interpretation is crucial for prenatal diagnosis, but high annotation costs and operator-induced variance make unsupervised pre-training a highly promising paradigm. However, existing pre-training methods largely ignore US-specific characteristics -- severe data redundancy, fan-shaped locality, and polar coordinate beamforming -- limiting their effectiveness in downstream tasks. To address this, we propose PolarMAE, a novel and efficient pre-training framework tailored for US images. Specifically, to mitigate continuous scanning redundancy, we introduce a Progressive Visual-Semantic Screening (PVSS) that adaptively extracts high-value samples, significantly boosting pre-training efficiency. Furthermore, we design an Acoustic-Bounded Region Constraint (ABRC) to accommodate US locality, forcing the model to focus strictly on valid acoustic regions rather than invalid dark backgrounds. Finally, leveraging the beamforming prior and local details, we propose a Polar-Texture Collaborative Masking (PTCM), enabling the model to capture underlying radial imaging patterns and critical tissue structures. Extensive experiments across diverse datasets and downstream interpretation tasks demonstrate that our method achieves state-of-the-art performance with strong pre-training scalability and efficiency.

Meng Lv, Yapeng Li, Hang Su +2

Wuhan University

Masked AutoencodersSelf-Supervised Pre-TrainingUltrasound ImagingMedical Image Representation LearningMasked Image Modeling
AskPDF
Apr 16, 2026

Co-distilled attention guided masked image modeling with noisy teacher for self-supervised learning on medical images

Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feature representations from unannotated data. Predominantly used random masking methods make SSL less effective for medical images due to the contextual similarity of neighboring patches, leading to information leakage and SSL simplification. Hierarchical shifted window (Swin) transformer, a highly effective approach for medical images cannot use advanced masking methods as it lacks a global [CLS] token. Hence, we introduced an attention guided masking mechanism for Swin within a co-distillation learning framework to selectively mask semantically co-occurring and discriminative patches, to reduce information leakage and increase the difficulty of SSL pretraining. However, attention guided masking inevitably reduces the diversity of attention heads, which negatively impacts downstream task performance. To address this, we for the first time, integrate a noisy teacher into the co-distillation framework (termed DAGMaN) that performs attentive masking while preserving high attention head diversity. We demonstrate the capability of DAGMaN on multiple tasks including full- and few-shot lung nodule classification, immunotherapy outcome prediction, tumor segmentation, and unsupervised organs clustering.

Jue Jiang, Aneesh Rangnekar, Harini Veeraraghavan

Memorial Sloan Kettering Cancer Center

Masked AutoencodersSelf-Supervised Pre-TrainingMedical Image Representation LearningMasked Image Modeling
AskPDF
Apr 14, 2026

Brain-DiT: A Universal Multi-state fMRI Foundation Model with Metadata-Conditioned Pretraining

Current fMRI foundation models primarily rely on a limited range of brain states and mismatched pretraining tasks, restricting their ability to learn generalized representations across diverse brain states. We present Brain-DiT, a universal multi-state fMRI foundation model pretrained on 349,898 sessions from 24 datasets spanning resting, task, naturalistic, disease, and sleep states. Unlike prior fMRI foundation models that rely on masked reconstruction in the raw-signal space or a latent space, Brain-DiT adopts metadata-conditioned diffusion pretraining with a Diffusion Transformer (DiT), enabling the model to learn multi-scale representations that capture both fine-grained functional structure and global semantics. Across extensive evaluations and ablations on 7 downstream tasks, we find consistent evidence that diffusion-based generative pretraining is a stronger proxy than reconstruction or alignment, with metadata-conditioned pretraining further improving downstream performance by disentangling intrinsic neural dynamics from population-level variability. We also observe that downstream tasks exhibit distinct preferences for representational scale: ADNI classification benefits more from global semantic representations, whereas age/sex prediction comparatively relies more on fine-grained local structure.

Junfeng Xia, Wenhao Ye, Xuanye Pan +3

Department of Biomedical Engineering, Southern University of Science and Technology, China · School of Biomedical Engineering, Shenzhen University, China

Medical Imaging Foundation ModelsDiffusion TransformerSelf-Supervised Pre-TrainingfMRI Foundation ModelsNeuroimagingConditional Diffusion Models+1
AskPDF
Apr 13, 2026

Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge

Clinical deployment of automated brain MRI analysis faces a fundamental challenge: clinical data is heterogeneous and noisy, and high-quality labels are prohibitively costly to obtain. Self-supervised learning (SSL) can address this by leveraging the vast amounts of unlabeled data produced in clinical workflows to train robust foundation models that adapt out-of-domain with minimal supervision. However, the development of foundation models for brain MRI has been limited by small pretraining datasets and in-domain benchmarking focused on high-quality, research-grade data. To address this gap, we organized the FOMO25 challenge as a satellite event at MICCAI 2025. FOMO25 provided participants with a large pretraining dataset, FOMO60K, and evaluated models on data sourced directly from clinical workflows in few-shot and out-of-domain settings. Tasks covered infarct classification, meningioma segmentation, and brain age regression, and considered both models trained on FOMO60K (method track) and any data (open track). Nineteen foundation models from sixteen teams were evaluated using a standardized containerized pipeline. Results show that (a) self-supervised pretraining improves generalization on clinical data under domain shift, with the strongest models trained out-of-domain surpassing supervised baselines trained in-domain. (b) No single pretraining objective benefits all tasks: MAE favors segmentation, hybrid reconstruction-contrastive objectives favor classification, and (c) strong performance was achieved by small pretrained models, and improvements from scaling model size and training duration did not yield reliable benefits.

Asbjørn Munk, Stefano Cerri, Vardan Nersesjan +81

Medical Imaging Foundation ModelsSelf-Supervised Pre-TrainingDomain GeneralizationMedical Image BenchmarksFew-Shot Medical Image Segmentation
AskPDF
Apr 13, 2026

Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization

Background: Task-specific microscopy datasets are often small, making it difficult to train deep learning models that learn robust features. While self-supervised learning (SSL) has shown promise through pretraining on large, domain-specific datasets, generalizability across datasets with differing staining protocols and channel configurations remains underexplored. We investigated the generalizability of SSL models pretrained on ImageNet-1k and HPA FOV, evaluating their embeddings on OpenCell with and without fine-tuning, two channel-mismatch strategies, and varying fine-tuning data fractions. We additionally analyzed single-cell embeddings on a labeled OpenCell subset. Result: DINO-based ViT backbones pretrained on HPA FOV or ImageNet-1k transfer well to OpenCell even without fine-tuning. Fine-tuning further improved performance to 0.704 ±\pm 0.027 (17 classes, multi-class labels). At the single-cell level, the HPA single-cell-pretrained model achieved the highest k-nearest neighbor performance across all neighborhood sizes (macro F1F_1 ≥\geq 0.515). Conclusion: SSL methods like DINO, pretrained on large domain-relevant datasets, enable effective use of deep learning features for fine-tuning on small, task-specific microscopy datasets.

Ben Isselmann, Dilara Göksu, Heinz Neumann +1

Department of Mathematics and Natural Sciences, Hochschule Darmstadt, Schoefferstraße 3, Darmstadt, 64295, Hessen, Germany. · Department of Chemical Engineering and Biotechnology, Hochschule Darmstadt, Stephanstrasse 7, Darmstadt, 64295, Hessen, Germany. · European University of Technology, European Union. +1

Supervised Fine-TuningSelf-Supervised Pre-TrainingSelf-Supervised Visual Representation LearningMicroscopy Image Analysis
AskPDF
Apr 12, 2026

Self-supervised Pretraining of Cell Segmentation Models

Instance segmentation enables the analysis of spatial and temporal properties of cells in microscopy images by identifying the pixels belonging to each cell. However, progress is constrained by the scarcity of high-quality labeled microscopy datasets. Many recent approaches address this challenge by initializing models with segmentation-pretrained weights from large-scale natural-image models such as Segment Anything Model (SAM). However, representations learned from natural images often encode objectness and texture priors that are poorly aligned with microscopy data, leading to degraded performance under domain shift. We propose DINOCell, a self-supervised framework for cell instance segmentation that leverages representations from DINOv2 and adapts them to microscopy through continued self-supervised training on unlabeled cell images prior to supervised fine-tuning. On the LIVECell benchmark, DINOCell achieves a SEG score of 0.784, improving by 10.42% over leading SAM-based models, and demonstrates strong zero-shot performance on three out-of-distribution microscopy datasets. These results highlight the benefits of domain-adapted self-supervised pretraining for robust cell segmentation.

Kaden Stillwagon, Alexandra Dunnum VandeLoo, Benjamin Magondu +1

School of Computer Science, Georgia Institute of Technology · School of Materials Science and Engineering, Georgia Institute of Technology · Department of Biomedical Engineering, Georgia Institute of Technology +1

Instance SegmentationMicroscopy Image AnalysisSelf-Supervised Pre-Training
AskPDF
Apr 11, 2026

Masked Contrastive Pre-Training Improves Music Audio Key Detection

Self-supervised music foundation models underperform on key detection, which requires pitch-sensitive representations. In this work, we present the first systematic study showing that the design of self-supervised pretraining directly impacts pitch sensitivity, and demonstrate that masked contrastive embeddings uniquely enable state-of-the-art (SOTA) performance in key detection in the supervised setting. First, we discover that linear evaluation after masking-based contrastive pretraining on Mel spectrograms leads to competitive performance on music key detection out of the box. This leads us to train shallow but wide multi-layer perceptrons (MLPs) on features extracted from our base model, leading to SOTA performance without the need for sophisticated data augmentation policies. We further analyze robustness and show empirically that the learned representations naturally encode common augmentations. Our study establishes self-supervised pretraining as an effective approach for pitch-sensitive MIR tasks and provides insights for designing and probing music foundation models.

Ori Yonay, Tracy Hammond, Tianbao Yang

Department of Computer Science and Engineering, Texas A&M University

Music Information RetrievalAudio Representation LearningSelf-Supervised Pre-TrainingContrastive Learning
AskPDF
Apr 9, 2026

PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL

Supervised deep learning models for automated CTG analysis are typically constrained by narrowly curated labelled datasets and limited patient cohorts, leaving substantial volumes of physiologically informative clinical recordings untapped. To address this limitation, we propose Physiology-aware Representation Learning via Integrated Self-supervision and Metadata for CTG (PRISM-CTG), a clinically grounded self-supervised foundation model (FM) for CTG that leverages large-scale unlabelled recordings to learn transferable domain-level representations. PRISM-CTG is pretrained using a multi-view self-supervised framework that jointly optimises 3 complementary pretext objectives: random-projected guided masked signal reconstruction, clinical variable prediction, and feature classification. Each objective is associated with a dedicated task-specific token, enabling specialised representation learning, while controlled cross-attention facilitates information exchange across clinical context. By reframing patient metadata and domain knowledge, which are often underutilised in conventional training as prediction targets, Prism-CTG transforms readily available clinical information into additional supervisory targets that guide clinically meaningful representation learning. Extensive experiments across 7 downstream CTG tasks in both antepartum and intrapartum domains demonstrated that PRISM-CTG consistently outperforms in-domain and SSL baselines. Notably, PRISM-CTG demonstrated strong generalisation under external validation on 2 datasets, while achieving comparable performance to studies trained on substantially larger, privately labelled datasets. To our knowledge, this is the first study to introduce large-scale FM for CTG that learns domain-level representations.

Sheng Wong, Ravi Shankar, Beth Albert +5

Nuffield Department of Women’s & Reproductive Health, University of Oxford, United Kingdom · OXDHL, University of Oxford, Oxford, United Kingdom · OATML, Department of Computer Science, University of Oxford, United Kingdom +1

Self-Supervised Time Series Representation LearningSelf-Supervised LearningSelf-Supervised Pre-Training
AskPDF
Apr 8, 2026

Towards foundation-style models for energy-frontier heterogeneous neutrino detectors via self-supervised pre-training

Accelerator-based neutrino physics is entering an energy-frontier regime in which interactions reach the TeV scale and produce exceptionally dense, overlapping detector signatures. In this regime, event interpretation becomes impractical for conventional reconstruction approaches, particularly when labelled data are scarce and the analysis spans diverse downstream objectives. We present a sparse ViT framework for learning reusable representations from heterogeneous detector data. Self-supervised pre-training combines masked autoencoder reconstruction with relational voxel-level objectives for hierarchy, ghost and particle identification, and the resulting shared encoder is then jointly fine-tuned across classification and regression tasks. Evaluated on simulated events from the proposed FASERCal concept at the LHC, we find that pre-training consistently improves neutrino flavour and charm-quark identification, momentum regression, and vertex reconstruction over training from scratch, with the addition of relational objectives yielding further gains in the most topologically complex channels. Interpretability analyses further show that pre-training yields a more structured latent space, while detector-subsystem ablations recover physically plausible channel-dependent roles for the heterogeneous inputs. A data-efficiency study shows that, with roughly 10310^3 labelled events, the pre-trained encoder already matches the flavour-classification performance of a randomly initialised model trained on an order of magnitude more data. The learned representations also transfer effectively to publicly available benchmarks spanning different detector technologies and energy scales, matching or exceeding published baselines. These results support self-supervised pre-training on multimodal detector data as a scalable route towards reusable representations for neutrino and particle-detector analysis.

Saúl Alonso-Monsalve, Fabio Cufino, Umut Kose +2

IPA, ETH Zürich, Otto Stern Weg 5, Zurich, 8093, Switzerland.

Self-Supervised Pre-TrainingHigh-Energy PhysicsMultimodal PretrainingMasked Autoencoders
AskPDF
Apr 8, 2026

VAMAE: Vessel-Aware Masked Autoencoders for OCT Angiography

Optical coherence tomography angiography (OCTA) provides non-invasive visualization of retinal microvasculature, but learning robust representations remains challenging due to sparse vessel structures and strong topological constraints. Many existing self-supervised learning approaches, including masked autoencoders, are primarily designed for dense natural images and rely on uniform masking and pixel-level reconstruction, which may inadequately capture vascular geometry. We propose VAMAE, a vessel-aware masked autoencoding framework for self-supervised pretraining on OCTA images. The approach incorporates anatomically informed masking that emphasizes vessel-rich regions using vesselness and skeleton-based cues, encouraging the model to focus on vascular connectivity and branching patterns. In addition, the pretraining objective includes reconstructing multiple complementary targets, enabling the model to capture appearance, structural, and topological information. We evaluate the proposed pretraining strategy on the OCTA-500 benchmark for several vessel segmentation tasks under varying levels of supervision. The results indicate that vessel-aware masking and multi-target reconstruction provide consistent improvements over standard masked autoencoding baselines, particularly in limited-label settings, suggesting the potential of geometry-aware self-supervised learning for OCTA analysis.

Ilerioluwakiiye Abolade, Prince Mireku, Kelechi Chibundu +4

Federal University of Agriculture Abeokuta, Nigeria · ML Collective · Ashesi University, Ghana +1

Masked AutoencodersSelf-Supervised Pre-TrainingMedical ImagingRetinal Vessel Segmentation
AskPDF
Apr 5, 2026

Entropy, Disagreement, and the Limits of Foundation Models in Genomics

Foundation models in genomics have shown mixed success compared to their counterparts in natural language processing. Yet, the reasons for their limited effectiveness remain poorly understood. In this work, we investigate the role of entropy as a fundamental factor limiting the capacities of such models to learn from their training data and develop foundational capabilities. We train ensembles of models on text and DNA sequences and analyze their predictions, static embeddings, and empirical Fisher information flow. We show that the high entropy of genomic sequences -- from the point of view of unseen token prediction -- leads to near-uniform output distributions, disagreement across models, and unstable static embeddings, even for models that are matched in architecture, training and data. We then demonstrate that models trained on DNA concentrate Fisher information in embedding layers, seemingly failing to exploit inter-token relationships. Our results suggest that self-supervised training from sequences alone may not be applicable to genomic data, calling into question the assumptions underlying current methodologies for training genomic foundation models.

Maxime Rochkoulets, Lovro Vrček, Mile Šikić

Genome Institute of Singapore, A*STAR, Singapore · KU Leuven, Belgium · Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia

Genomic Foundation ModelsGenomicsSelf-Supervised Pre-TrainingSequence ModelingMolecular Representation Learning
AskPDF
Apr 5, 2026

PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities

Multimodal self-supervised pretraining offers a promising route to cancer prognosis by integrating histopathology whole-slide images, gene expression, and pathology reports, yet most existing approaches require fully paired and complete inputs. In practice, clinical cohorts are fragmented and often miss one or more modalities, limiting both supervised fusion and scalable multimodal pretraining. We propose PRIME, a missing-aware multimodal self-supervised pretraining framework that learns robust and transferable representations from partially observed cohorts. PRIME maps heterogeneous modality embeddings into a unified token space and introduces a shared prototype memory bank for latent-space semantic imputation via patient-level consensus retrieval, producing structurally aligned tokens without reconstructing raw signals. Two complementary pretraining objectives: inter-modality alignment and post-fusion consistency under structured missingness augmentation, jointly learn representations that remain predictive under arbitrary modality subsets. We evaluate PRIME on The Cancer Genome Atlas with label-free pretraining on 32 cancer types and downstream 5-fold evaluation on five cohorts across overall survival prediction, 3-year mortality classification, and 3-year recurrence classification. PRIME achieves the best macro-average performance among all compared methods, reaching 0.653 C-index, 0.689 AUROC, and 0.637 AUROC on the three tasks, respectively, while improving robustness under test-time missingness and supporting parameter-efficient and label-efficient adaptation. These results support missing-aware multimodal pretraining as a practical strategy for prognosis modeling in fragmented clinical data settings.

Kai Yu, Shuang Zhou, Yiran Song +9

Division of Computational Health Sciences, Department of Surgery, University of Minnesota, Minneapolis, MN, USA. · University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. · North Carolina State University, Raleigh, NC, USA. +2

Multimodal PretrainingMissing-Modality LearningSelf-Supervised Pre-TrainingCancer Survival PredictionIncomplete Data Imputation
AskPDF
Apr 3, 2026

CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data

Recent work suggests that large-scale, multi-animal modeling can significantly improve neural recording analysis. However, for functional calcium traces, existing approaches remain task-specific, limiting transfer across common neuroscience objectives. To address this challenge, we propose CalM, a self-supervised neural foundation model trained solely on neuronal calcium traces and adaptable to multiple downstream tasks, including forecasting and decoding. Our key contribution is a pretraining framework, composed of a high-performance tokenizer mapping single-neuron traces into a shared discrete vocabulary, and a dual-axis autoregressive transformer modeling dependencies along both the neural and the temporal axis. We evaluate CalM on a large-scale, multi-animal, multi-session dataset. On the neural population dynamics forecasting task, CalM achieves competitive performance against strong specialized baselines after pretraining. With a task-specific head, CalM further adapts to the behavior decoding task and achieves superior results compared with supervised decoding models. Moreover, linear analyses of CalM representations reveal interpretable functional structures beyond predictive accuracy. Taken together, we propose a novel and effective self-supervised pretraining paradigm for foundation models based on calcium traces, paving the way for scalable pretraining and broad applications in functional neural analysis. Code is released at https://github.com/TSuXinH/CalM.

Xinhong Xu, Yimeng Zhang, Qichen Qian +1

Department of Automation, Tsinghua University, Beijing, China · School of Life Sciences, Tsinghua University, Beijing, China

Self-Supervised Pre-TrainingTime-Series Foundation ModelsNeural Decoding
AskPDF