Self-Supervised Learning

Also known as SSL

Overview

Self-supervised learning creates training signals from the data itself, for example by matching augmented views, predicting masked content, or using temporal, geometric, and physical consistency. Contrastive learning, masked autoencoders, teacher–student distillation, and joint-embedding predictive architectures are common approaches across images, video, audio, language, medical data, and scientific measurements. These methods can reduce dependence on costly labels and support transfer, but useful representations depend on how well the pretext signal fits the data and downstream task. A central tension is balancing invariance and non-collapse with retaining fine-grained information, while establishing reliable transfer under domain shifts and limited compute remains an open challenge.

Latest papers

280 papers27 papers in the last four weeks, down 13% on the four weeks before. 0.2% of all new papers.

Sep 21, 2026

Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors

Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trained image encoders are standard in robot learning pipelines, tactile encoders are still commonly trained from scratch from raw, noisy signals, which might limit their expressivity. Existing self-supervised learning (SSL) approaches focus predominantly on vision-based tactile sensors, leaving distributed electronic skins largely unaddressed. These sensors, however, have a distinctive property: their sensing elements are sparse and irregularly arranged over the surface they cover, which makes direct reuse of visual SSL methods suboptimal. We present Tactile-JEPA, an efficient self-supervised pre-training method that uses the spatial arrangement of tactile sensors to learn topology-aware representations. Specifically, it is trained to predict the embeddings of masked sensing elements from the unmasked remainder, using the sensor connectivity graph to guide spatial masking. Our analysis shows that effective tactile representations require capturing both local contact details and the global state of the tactile surface, which we achieve through dual-scale masking. Across three diverse datasets spanning magnetic and piezoresistive sensors, different robot embodiments, and single- and paired-sensor configurations, Tactile-JEPA reduces force estimation error by 6.3% and in-hand orientation error by 20.8% over the prior state-of-the-art, with consistent gains in other downstream applications, including policy learning. Overall, our results demonstrate that the benefit of tactile sensing depends critically on the quality of encoder pre-training, a problem which Tactile-JEPA addresses directly. Code is available at https://github.com/E-Kovtun/tactile.
Sep 21, 2026

TReViS: Temporal Repetition Structure Aware Video Synthesis for Self-supervised Repetitive Action Counting

Fully supervised repetitive action counting (RAC) has achieved strong performance, but requires dense temporal annotations that are costly and difficult to scale. We propose TReViS, a self-supervised video synthesis framework that enables training RAC models without any repetition labels. TReViS estimates the underlying temporal repetition structure of an unlabeled video via a Temporal Self-Similarity Matrix, infers its cycle statistics, and synthesizes new training sequences that preserve realistic repetition patterns while introducing controlled temporal variability. These synthesized videos are paired with pseudo-labels and used to train existing RAC architectures from scratch. Across multiple datasets and backbones, TReViS consistently outperforms prior self-supervised methods and achieves performance competitive with several supervised baselines, while remaining fully label-free, demonstrating the effectiveness of structure-aware video synthesis for label-free RAC. The source code is available at https://github.com/yfqi/TReViS.
Sep 14, 2026

Sharp Regret Bounds and a Task-Covariance Correction for Spectral Representation Learning

Spectral contrastive learning keeps the kk directions along which two views of the data depend most strongly, while downstream tasks may need other directions. Existing guarantees for spectral features assume that the distribution of tasks has no preferred direction. We show that this isotropy condition is the wrong criterion. With linear probing, the task distribution affects the average probing gain only through the matrix BΛB⊤BΛB^\top, where BB records the dependence between views and ΛΛ is the task covariance: optimal features span its top-kk eigenspace, whereas spectral features span that of BB⊤BB^\top. Transfer therefore depends on alignment, and strongly uneven task preferences cost nothing when they favour the spectral directions. Otherwise the regret of spectral features is at most linear in the anisotropy of ΛΛ. No representation chosen without task information improves this rate when the leading spectrum is flat, and a spectral gap makes it quadratic. With labelled tasks, the same matrix gives a correction: Fisher discriminant directions for a frozen encoder, or a one-term change to the spectral contrastive loss. We bound the regret of the correction by the error in estimating BΛB⊤BΛB^\top, and compare this error with the misalignment of spectral features to decide when to correct. The analysis extends to finite samples, continuous variables and noisy views. Correction reduces synthetic held-out regret from 0.8580.858 to 0.0030.003 with 20002000 labelled tasks, and the decision rule gives the lowest regret among the tested rules at every bank size. On CIFAR-100, spectral features of frozen encoders keep most of the task signal on unseen classes, and where a bank of other classes would lower accuracy, the rule keeps them in every case.
Sep 13, 2026

S3-Tracker: Self-Supervised Surgical Tissue Tracking With Contrastive Random Walks

Robust point tracking in endoscopic videos is essential for computer-assisted intervention and autonomous robotic surgery, enabling continuous registration between intraoperative video and preoperative imaging despite soft tissue deformation. However, supervised tracking methods depend on large annotated datasets, while surgical conditions make reliable trajectory annotation challenging. We propose a self-supervised Track-Any-Point approach that learns from unlabeled surgical videos by establishing global pixel correspondences and inferring point trajectories through contrastive random walks. Trained without annotations, our method achieves performance comparable to existing semi-supervised approaches while implicitly handling tissue deformation. These findings demonstrate the feasibility of self-supervised point tracking in surgical environments and its potential to reduce reliance on annotated data.
Sep 10, 2026

Self-Supervised Cardiac Phase Detection via Single-Parameter Latent Orbits

Accurate identification of end-diastole (ED) and end-systole (ES) in echocardiography underpins the quantification of ventricular function, yet manual selection of these key frames is subjective and introduces clinically significant inter-operator variability. Recent self-supervised methods either prescribe strict periodic trajectories or learn an unconstrained low-dimensional motion subspace from reconstruction or registration objectives. The former offers interpretability but imposes restrictive assumptions on temporal progression, whereas the latter leaves cardiac phase implicit and ED/ES must be recovered through post-hoc geometric processing of the learned trajectory. We translate the physiological observation that cardiac phase is a one-dimensional signal into a prior by constraining the latent motion component to a single-parameter latent orbit, i.e., a global linear trajectory in latent space indexed by a bounded scalar phase variable. Mapping this variable through a sinusoidal nonlinearity yields an oscillatory motion signal with consistent temporal ordering, enabling direct identification of ED and ES from the learned phase signal. This inductive bias allows the model to capture an interpretable representation of the cardiac cycle, while maintaining flexibility to capture irregular heartbeats. Trained on EchoNet-Dynamic without annotations, our minimal single-parameter cardiac phase model learns an effective latent orbit, significantly improves upon the previous state of the art in ED localisation and matches it in ES localisation while using a more constrained representation and fewer training epochs. This demonstrates that a principled physiological inductive bias can match or exceed the performance of more complex representations. Code is available at: https://github.com/BonniciJ/OrbitalEcho/
Sep 8, 2026

"Transforming" LHCb: self-supervised maps of heavy-flavour decays

Decays of beauty and charm hadrons provide sensitive probes of physics beyond the standard model, including decays with invisible particles, in which part of the final state leaves no reconstructed detector signature. The large heavy-flavour data samples recorded by the LHCb experiment at the CERN LHC, together with its precise tracking, displaced vertex reconstruction, and particle identification, make it particularly well suited to learning a map of reconstructed heavy-hadron decay environments directly from data. We propose to bring recent advances in jet flavour tagging at ATLAS and CMS to significantly improve on the performance of the current LHCb taggers and extend them to the reconstruction of heavy-flavour decays with several invisible particles in the final state. To achieve this, we introduce a self-supervised transformer architecture that learns the decay maps without flavour or exclusive-decay labels by inferring masked particle identification information and completing jets from which constituents have been removed. Across five classification tasks in simulated LHCb Open Data, the self-supervised model outperforms an otherwise identical transformer with random weights, and performs comparably to a fully supervised transformer. We achieve a tagging power of about 10%. In addition, removing constituents from reconstructed exclusive decays also systematically increases the model anomaly score relative to random removals from the same heavy hadrons. We confirm this behaviour directly in 2017 LHCb proton-proton collision Open Data: the score increases for all eight studied heavy-flavour channels, and the signal region response exceeds that in the adjacent sidebands. These studies provide a proof of principle that mapping heavy-flavour decay environments through jets can transform flavour tagging in LHCb and extend the discovery reach for incomplete or otherwise unusual decays.
Sep 8, 2026

Effects of model architecture and learning strategies on deep learning-based recognition of activated sludge microscopic images and comparison with quantitative image analysis

Microscopic image analysis has long been recognized as a promising approach for monitoring activated sludge. In recent years, deep learning-based image analysis has been increasingly adopted in this field because of its high performance. However, previous studies on microscopic image analysis of activated sludge have rarely explored transformer-based models or self-supervised foundation models and have instead relied on CNNs and supervised ImageNet pretraining. In addition, previous studies often downsampled image sizes, but the effects of downsampling have not been sufficiently investigated, and the relationship between downsampling strategies and image analysis performance remains unclear. Furthermore, no study has quantitatively compared deep learning performance with quantitative image analysis (QIA), which was widely used before the emergence of deep learning. In this study, to examine how model architecture and learning strategies affect performance in microscopic image analysis of activated sludge and to quantitatively determine whether deep learning outperforms QIA, we prepared three types of activated sludge samples, classified their microscopic images, and evaluated classification accuracy. Our results showed that transformer-based architectures and alternative pretraining methods were effective in terms of classification accuracy. Our downsampling analysis showed that using overly small images reduced accuracy, but increasing image size beyond a certain point did not improve it further. In addition, the analysis indicated that, to achieve high classification accuracy, maintaining the field of view was a more effective downsampling strategy than maintaining resolution. Finally, our comparison between deep learning and QIA showed that deep learning outperformed QIA in terms of accuracy.
Sep 8, 2026

Revisiting Spectral Representations in Generative Diffusion Models

Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate training convergence and enhance sampling quality, yet the mechanism driving this synergy remains insufficiently understood. In this paper, we investigate the connection between self-supervised spectral representation learning and diffusion generative models through a shared perspective on perturbation kernels. On the diffusion side, samples (e.g., images, videos) are produced by reversing a stochastic noise-injection process specified by Gaussian kernels; on the spectral representation side, spectral embeddings emerge from contrasting positive and negative relations induced by random perturbation kernels. Motivated by this, we propose a self-supervised spectral representation alignment method to facilitate diffusion model training. In addition, we clarify how joint spectral learning can benefit diffusion training from a geometric perspective. Furthermore, we find that the optimization of the spectral alignment objective is in an equivalent form of diffusion score distillation in the representation space. Building on these findings, we integrate a spectral regularizer into diffusion training objectives to improve the performance of diffusion models on multiple datasets. Experiments across images and 3D point clouds show consistent gains in generation quality. Code is released at https://github.com/yuehaowang/spectral-reg-diffusion.
Sep 7, 2026

Self-Supervised Multi-View 3D Gaze Target Estimation via Probabilistic Ray Marching

We present a self-supervised approach, Self-MVGTE, for estimating 3D gaze targets from multiple camera views. Unlike existing methods that independently estimate 2D gaze targets per camera view, Self-MVGTE predicts gaze targets directly in 3D space for the first time. Moreover, it does not require any ground-truth annotations from the target scene and uses only the multi-view input images from a calibrated camera setup, pseudo 2D gaze target labels from a monocular gaze target estimation model, and 3D gaze vectors from a monocular 3D gaze estimation model. A key challenge is that these pseudo labels are inherently noisy and multi-view inconsistent. To address this, we propose a probabilistic ray marching framework, which models the uncertainty of these pseudo labels and exploits 3D gaze vectors as geometric priors. Specifically, these gaze vectors are first integrated into the monocular gaze target estimation model to improve its generalization to unseen scenes, producing higher-quality pseudo labels. Then, for 3D gaze target estimation, we construct a 3D gaze cone by casting a bundle of rays from the eye position around the gaze vector to strictly constrain the solution space. Within this cone, we propose a depth-guided feature sampling strategy using off-the-shelf DINOv2 and Depth-Anything-3 models, and estimate a spatial likelihood distribution of the gaze target. Finally, we convert the pseudo gaze target labels into a target distribution and softly optimize the network. Extensive experiments on the MVGT dataset show that Self-MVGTE achieves state-of-the-art performance, surpassing existing fully-supervised baselines.
Sep 5, 2026

DINO Eats Geometry: Self-Supervised Sign Representations that Absorb Articulated Hand Geometry

Handshape and orientation are geometric components of sign language, yet many sign encoders learn from appearance alone. We introduce SignDEG (DINO Eats Geometry), a temporal sign encoder that uses articulated hand geometry as a pre-training target and requires only video at inference. Frozen DINOv3 features of tracked hands and faces feed per-stream temporal Transformers. Geometric latent prediction (GLP) supervises an intermediate block with WiLoR latents, MANO articulation, and 3D joints, including at masked frames. Geometric relation transfer (GRT) matches cross-video frame-similarity distributions at the final block. Both objectives are learned jointly with temporal self-distillation; WiLoR and the geometry heads are then discarded. Under the SHuBERT public-data evaluation protocol, SignDEG reaches 17.9/24.5 BLEU-4 on How2Sign/OpenASL, compared with 16.2/23.2 for SHuBERT. Rank-1 adaptation improves ASL Citizen and Sem-Lex recognition by 0.02 Recall@1 each, and phonological classification improves across 16 attributes. Removing GRT while retaining GLP reduces How2Sign BLEU-4 by 1.4 and ASL Citizen Recall@1 by 0.034. The results support transferring articulated structure into an appearance encoder without running a hand reconstruction model at deployment.
Sep 4, 2026

Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference

Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two factors: the labor-intensive manual annotation of cognacy judgments required for character-based methods and the substantial computational cost of inference on large datasets. This paper introduces a fully self-supervised contrastive learning framework that learns lexical representations directly from raw IPA-transcribed wordlists, without requiring cognacy annotations, alignments, or additional expert input. The model employs a dual contrastive objective: a word-level loss that organizes phonetically similar forms into a coherent space, and an auxiliary language-level loss that encourages the lexical space to reflect broader phonological properties of languages. From the resulting word representations, pairwise language distances are derived and used to infer a global phylogenetic tree of 3,399 language varieties. The inferred tree achieves a generalized quartet distance (GQD) to the Glottolog reference tree competitive with multiple baselines, while requiring only minutes of computation on a standard notebook GPU. Furthermore, the same representations capture diachronic concept stability: variance in pairwise distances across languages yields stability rankings that correlate significantly with established rankings. Ablation studies confirm that both the language-level objective and the use of phonetic feature vectors improved the inferred trees topology with regards to GQD. The framework thus provides a computationally efficient and fully automatic alternative for large-scale phylogenetic inference and offers a unified representation supporting downstream analyses at both the language and concept level.
Sep 4, 2026

An Analysis of Self-supervised Pre-training with Dependent Samples

Self-supervised learning relies on so-called data augmentations φ(x)φ(x) of unlabeled datapoints xx --- for example, masking random pixels in an image xx --- that should leave the label of xx invariant and are often used to learn a lower-complexity invariant subspace V\cal V for downstream tasks. In practice, such augmentations {φl(xi)}\{ φ_l(x_i) \} are pooled together to learn V\cal V, despite obvious inter-dependencies between different augmentations φl(x),φk(x)φ_l(x), φ_k(x) of the same datapoint xx. However, theoretical works on the subject typically consider procedures that avoid such dependencies, and are therefore limited to operate on smaller subsets of independent data. We show in this work that pooling augmentations together, despite inter-dependencies, is a better alternative than the baseline of partitioning the data into subsets of independent data. More precisely, in the context of estimating V\cal V, the statistical estimation error bounds for pooling are never worse than the partitioning baseline, and in some cases --- such as masking or noise injection-based augmentations over a shallow neural network --- naive pooling leads to faster rates in terms of the number of augmentations. The benefits of pooling are particularly prominent when the correlations between different augmentations φl(x),φk(x)φ_l(x), φ_k(x) have mild effects on estimation or help decrease the estimation variance. The analysis, therefore, yields new insights into the success of pooling augmented samples in self-supervised pre-training, and provides an intuition behind the practical preference towards using many augmentations.
Sep 3, 2026

The microscope is the mask: privileged views and labels from a cryo-ET forward model

We explore the use of simulated data for training a model for protein annotation in crowded cryo-electron tomography volumes reconstructed from images collected at limited tilt angles and severely corrupted by the measurement operator. Firstly, we leverage the corruptions imposed by the forward model to generate domain-specific augmented paired views of the exact same scene for an invariance objective integrated into the LeJEPA self-supervised training framework. Secondly, we use additional information from the simulation pipeline such as the positions and identity of proteins in the simulated volumes to inform the architecture of the model and the loss function, so that semantic information is localised at protein positions in the resulting dense feature volume. The resulting model, CARNIVAL, is evaluated without finetuning on classification and detection tasks in real tomograms, using a benchmark dataset containing multiple protein types and two tomogram processing types. We show that CARNIVAL outperforms a state-of-the-art model trained using a contrastive objective on simulated data but without forward model-based paired views or privileged information.
Sep 3, 2026

Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision

We introduce S3^3T (Self-Supervised Self-Distillation over Time), which, to the best of our knowledge, is the first fully self-contained framework for continuous video state tracking. Our method treats temporal sampling density as privileged information, based on the hypothesis that a denser view of the same clip recovers the running state more accurately. This view serves as the teacher, while a sparse-view student with the same weights learns to match its next-token distribution. The model generates its own target, so training requires no labels, separate teacher, or reward signal, and adds no inference cost. On LLaVA-OneVision-2-8B, S3^3T improves VSTAT accuracy by +1.74+1.74 as a single model, +2.38+2.38 with souping, and +2.70+2.70 with additional vision-encoder adaptation, while prior self-evolving methods leave state tracking largely unchanged. The capability learned from unlabeled synthetic clips transfers to real videos, improving performance by +7.95+7.95 on VSTAT-YouTube state-tracking questions and +4.50+4.50 on MVBench Action Count.
Sep 3, 2026

P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing

Advances in neural rendering have enabled high-fidelity multi-view reconstruction of 3D scenes. However, free-form non-rigid shape editing remains a significant challenge. Point-based neural representations are highly desirable for multi-view reconstruction because they lack fixed connectivity, which does not constrain the learned surface topology to that of the initialization. Yet this same property causes point-based representations to struggle with holes and surface discontinuities under large deformations. To address this, we propose a novel self-supervised method to enable point-based representations to adapt to large deformations without requiring ground truth multi-view images of deformed geometry. The key idea is to generate random deformations and to ensure consistency in the predicted surface before and after deformation. In particular, the surface prediction from the deformed point cloud should be the same as the deformation applied to the surface prediction from the original point cloud. We incorporate our approach into attention-based point representations, which differ from splatting-based point representations in their use of a learned interpolation kernel between points as opposed to a Gaussian kernel around each point. This learned interpolation kernel can learn to adapt to large deformations, without requiring addition or removal of points. We show that our framework significantly enhances its robustness to large deformations. Experiments on synthetic geometry editing benchmarks (Neural Editor, Objaverse) demonstrate that our approach outperforms existing point-based methods in zero-shot editing and significantly reduces artifacts. Furthermore, qualitative results on the DTU and Mip-NeRF 360 datasets demonstrate our method's effectiveness on real-world scenes.
Sep 2, 2026

Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning

This position paper argues that the absence of labels does not imply the absence of human supervision in visual learning, and urges the research community to identify sources of supervision more explicitly. Many recent methods in computer vision build upon representations learned from large-scale unlabeled data, and are therefore grouped under the same umbrella term unsupervised.'' However, different data curation schemes and training objectives embed substantially different human priors on which models rely, and we argue that one unsupervised'' umbrella term is no longer capturing these distinctions. This ambiguity makes it harder to compare unsupervised learning research conducted under different assumptions, coinciding with a sharp decline in papers titled with ``unsupervised'' in flagship computer vision conferences since 2021, despite continued growth of the field. While we fully embrace pre-training as a strong foundation for modern computer vision, we advocate for a community-level effort toward greater conceptual clarity: authors are encouraged to disclose priors in data selection and learning objectives, and to specify which components of a learning pipeline depend on which assumptions. Standardized disclosure practices can improve academic communication, ensure fairer comparisons, and preserve methodological diversity in unsupervised learning.
Sep 2, 2026

SMart: A Multi-source Multi-phase Time Series Representation Transfer Framework

Time series representation learning (TSRL) has attracted growing research interests in recent years. Two recent explorations in TSRL are: i) exploiting a transformer-based framework to learn time series; ii) instead of using only the targeted dataset, borrowing time series from other datasets to to facilitate representation transfer. While these two explorations are shown effective, the self-supervised time series recovery task in (i) and the single-source dataset used in (ii) are technically simple and thus can be enhanced with new ideas. In this work, we propose a new TSRL framework, namely multi-source multi-phase time series representation transfer (SMart), which has two novel mechanisms to address the aforementioned deficiencies: 1) a multi-phase recurrence plots recovery task, in three alternative modes, for guiding the encoder to embed time series dynamics into the time series representation; and 2) a source dataset selector to select multiple suitable source datasets to supplement the original target dataset for pre-training the TSRL encoder. Experimental results show that SMart outperforms several state-of-the-art models for time series representation learning, classification and regression on both uni-variate and multi-variate time series datasets, reducing mean absolute error up to 19.5% for time series regression, and increasing average accuracy up to 1.34% for time series classification.
Sep 1, 2026

Physics-Driven Independent Pair Generation for Iterative Self-Supervised Low-Dose CT Denoising

Low-dose computed tomography (LDCT) measurements contain mixed Poisson-Gaussian noise. However, most self-supervised methods rely on generic image statistics and do not explicitly model this noise, which may limit their ability to effectively suppress realistic LDCT noise. To address this issue, we propose a physics-driven framework with cross-domain iteration for self-supervised LDCT denoising. The proposed framework proceeds in three main steps. First, a learned sinogram prior and the LDCT noise model guide posterior inference of photon counts, enabling separation of the Poisson and Gaussian components. Second, the separated Poisson and Gaussian components are respectively processed by binomial thinning and Gaussian data thinning to construct two branches, and residual scaling matches each branch's noise level to that of the observation, yielding a training pair with approximately independent noise realizations from one low-dose measurement. Finally, the pair is used to train an image-domain network whose forward-projected outputs update the prior. Through cross-domain iteration, the prior and the training pair are progressively refined while maintaining consistency with CT acquisition physics. Experiments on simulated data from AAPM, LIDC-IDRI, and LoDoPaB-CT and on real LDCT data show consistent gains over the evaluated self-supervised baselines across dose levels, with performance comparable to the evaluated supervised baseline.
Aug 27, 2026

LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics

Video carries the temporal structure of the physical world, yet learning representations from it has remained computationally expensive: prevailing self-supervised methods either prevent representation collapse through architectural asymmetries, coupling an exponential-moving-average target encoder, a stop-gradient, and a capacity-limited predictor, or circumvent it by reconstructing masked content in pixel space. We introduce LeVJEPA, the first video encoder trained under LeJEPA's collapse-free objective, which dispenses with both. A single encoder is trained with an invariance loss over global and local views of a clip, regularized by SIGReg, which excludes collapse with a provable guarantee. The architecture reduces to an encoder and a projector, and the objective to a single hyperparameter. This formulation admits two properties. First, the cost of pretraining is governed by the number of tokens the encoder observes; uniform random token dropping renders this number small while simultaneously improving downstream accuracy. At matched epochs on identical data, LeVJEPA matches or surpasses V-JEPA 2 across ViT-S/B/L at 5.6 to 20.8x less pretraining compute, and at matched total FLOPs it exceeds the strongest video baseline by 7.6 points on ImageNet-1K while remaining competitive on motion-centric benchmarks. Second, since no asymmetry between branches is required, the encoder can be trained with block-causal attention at no measurable accuracy cost: temporal ordering becomes a property of the encoder itself. Against a compute-matched DINOv2 trained on frames of the same videos, LeVJEPA approaches the image-pretrained encoder on appearance-centric evaluation while nearly doubling its motion-centric accuracy. These results indicate that, once its computational overhead is removed, video becomes a viable and in several respects preferable substrate for general-purpose visual pretraining.
Aug 27, 2026

Domain-Specific Self-Supervised Representation Learning for Retinal Fundus Classification

Annotated medical images remain scarce and costly to obtain, which motivates self-supervised learning (SSL). We present a controlled empirical study of two SSL frameworks, SimSiam and SimCLR, for retinal fundus classification, asking whether retina-specific augmentations (Graham's local-mean subtraction and CLAHE) improve representations beyond standard augmentation and grayscale conversion. ResNet-18 backbones are pretrained on 48K unlabeled fundus images and evaluated by linear probing and fine-tuning on EDID (multi-disease) and RetinaMNIST (DR grading). On EDID, grayscale conversion accounts for most of SimSiam's linear-probe gain, and Graham or CLAHE add little on top of it. After fine-tuning, SimSiam with Graham+Gray exceeds an ImageNet-supervised baseline on RetinaMNIST (+3.0 accuracy points) but only matches it on EDID. Retina-specific augmentation therefore helps inconsistently and should be validated per SSL method and task.
Aug 25, 2026

Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfiguration

The proliferation of distributed energy resources (DERs) in distribution grids enables the active coordination of these assets to reduce costs and enable cleaner operations. Realizing this potential requires solving multiphase AC optimal power flow (AC-OPF) quickly across varying loads, DER availabilities, and topology reconfigurations, at much greater speed and scale than conventional nonlinear solvers. Learning-based surrogates can offer millisecond inference, yet existing methods target largely balanced transmission systems and do not scale to the multiphase, unbalanced, and reconfigurable nature of distribution feeders at utility scale. We present the Penalty + Sequential Linearized Feasibility Seeking (SLFS) algorithm, a self-supervised learning framework for multiphase distribution AC-OPF under switch-induced topology changes. Penalty+SLFS requires no labeled optimal solutions and trains directly from the AC-OPF objective and constraints through a differentiable fixed-point power flow solver, avoiding expensive label generation and admitting robust training procedures. Topology changes are handled efficiently using Sherman-Morrison-Woodbury updates of the admittance-matrix inverse, while an M-step Jacobian approximation accelerates differentiation through the power flow solver. At inference, SLFS repairs any infeasible predictions, providing feasibility guarantees with low computational overhead. On IEEE feeders ranging from 13 to 8,500 nodes, Penalty+SLFS achieves negligible optimality gaps and near-zero constraint violations, delivers up to three orders of magnitude speedups over IPOPT, and remains robust under large distributional shifts, demonstrating a viable path toward real-time, topology-aware AC-OPF for large-scale distribution grids.
Aug 25, 2026

ConsensusTAS: Self-Supervised Temporal Action Segmentation for Long-Horizon Construction Videos

Recognizing sequential construction activities is important for collaborative human-robot work; for example, robots are able to understand workers' current and upcoming actions and provide timely tool delivery or physical support. However, despite extensive research on construction worker activity recognition, existing studies have been limited to classifying activity categories, such as climbing, lifting, and walking, instead of recognizing fine-grained activity transitions from long-horizon sequences. Addressing this problem is challenging because annotating action temporal boundaries in long construction videos is time-consuming. In this study, we propose ConsensusTAS, a label-free, self-supervised learning approach to segment continuous video streams into distinct activity phases by exploiting the internal consensus of candidate segmentations. We evaluated our algorithm on three public datasets, where it outperformed state-of-the-art methods, achieving an F1@10 of 73.08 on GTEA, an F1@10 of 64.33 on Breakfast, and an F1@50 of 33.50 on static-camera videos from Assembly101. We also tested it on real-world construction videos, where post-hoc evaluation showed that the model successfully recognized and segmented actions within the composite activity of bricklaying, such as spreading mortar on a brick, placing the brick, pressing, and aligning. Compared with other temporal action segmentation models that require computationally intensive large vision-language models, our method can run on a CPU, which provides practical value for video surveillance and human-robot collaboration on mobile robotic platforms.
Aug 20, 2026

Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems

Self-supervised learning for imaging inverse problems is increasingly important in photon-limited settings, where acquiring clean ground truth is impractical and reconstruction must remain stable under dataset and acquisition shifts. This challenge is amplified under Poisson noise, whose signal-dependent statistics interact with sampling operators (e.g., CFA mosaicing). Meanwhile, foundation vision encoders trained at web scale offer distortion-invariant, content-related representations that generalize well across domains, suggesting a promising route to build priors that transfer beyond the training distribution without expensive fine-tuning. This paper proposes an ADMM-inspired unrolled plug-and-play solver for Poisson inverse problems that decouples a closed-form data-consistency update from a parameter-efficient prior. The prior is implemented as a lightweight decoder operating on frozen CLIP RN50 dense multi-scale features, adapting foundation representations with less trainable parameters. For self-supervision, the method integrates GR2R measurement-domain re-corruption with an Equivariant Imaging regularizer via virtual acquisitions. Experiments on Poisson CFA demosaicing and deblurring show competitive quality, improved robustness under shifts, and self-supervised performance approaching supervised training.
Aug 19, 2026

RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation

LiDAR scene flow estimates point-wise motion between two consecutive scans, referred to as the source and target. Leading self-supervised methods typically minimize the Chamfer loss, the nearest-neighbor distance between the flow-compensated source and the target. However, nearest-neighbor search does not enforce motion rigidity, often leading to inconsistent flows within object instances. Existing approaches address this issue with additional regularization terms, but flow consistency among points remains limited, especially for large objects. We propose RVLoss, a self-supervised loss that incorporates motion rigidity by design through a runoff vote mechanism. Our key observation is that the point-wise motion, calculated from nearest-neighbor search, can often be grouped into a small set of dominant flow candidates by voting (top-k voting). Furthermore, when compensating the source by these candidates, the flow that best represents the underlying rigid motion often yields the highest consensus after a second voting (top-1 voting). Based on this insight, we incorporate the two-stage runoff vote into loss design and create cluster-wise rigid flows and free-form flows as pseudo-labels for self-supervised learning. RVLoss can be seamlessly integrated into existing feedforward architectures. Experiments on the Argoverse2 2026 Scene Flow Challenge show that models trained with RVLoss achieve state-of-the-art performance among self-supervised approaches, outperforming baseline models trained with alternative loss designs by 20% and reducing the mean dynamic normalized end-point error from 0.202 to 0.163. Moreover, cross-dataset evaluations demonstrate consistent performance improvements across four additional datasets. Code is available at https://github.com/tudelft-iv/RVLoss.
Aug 16, 2026

TransfHAR: Self-Supervised Wrist Representations for On-Demand Activity Recognition

Fine-grained wrist activity recognition can support applications such as procedural step guidance and context-aware assistance, yet acquiring labeled data for every new task, user, and activity granularity remains a bottleneck. We present TransfHAR, a self-supervised wrist IMU framework for on-demand, fine-grained activity recognition by learning transferable motion priors from global, unlabeled activities. We show that self-supervised pretraining on coarse wrist IMU activities (e.g., sitting, walking, exercise) learns motion structure rich enough to transfer to fine-grained manipulative, gestural, and procedural activities (e.g., snapping, stirring, waving) that are absent from pretraining. We implement TransfHAR as a real-time smartwatch application that lets users define and expand their own activity set for personalized recognition from only a few demonstrations. Across three offline cross-dataset evaluations, TransfHAR matches or exceeds fully supervised baselines that use complete label sets with equal or additional sensor channels, by 6.2 balanced-accuracy points on average. In an in-lab study with 10 participants each performing seven novel wrist activities, TransfHAR reaches 86.7% balanced accuracy across participants with five examples per class and 90.4% when updated from a single one-minute recording per class. These results indicate that broad self-supervised wrist pretraining provides an effective foundation for on-demand fine-grained activity recognition.
Aug 16, 2026

CrevasseSeg: A Label-Efficient UAV Crevasse Segmentation Framework

Crevasse mapping from uncrewed aerial vehicle (UAV) imagery matters for glaciological research and for field safety in glaciated terrain. Yet, pixel-level annotation of glacier surfaces is costly and requires domain experts. We introduce CrevasseSeg, a framework for binary segmentation over the terminus of Borebreen, Svalbard, comprising 1,938 unlabelled UAV orthomosaic tiles for self-supervised/unsupervised fine-tuning, 24 labelled tiles for validation and 176 labelled tiles for testing. Using CrevasseSeg, we benchmark five self-supervised objectives -- BYOL, a Jensen-Shannon Divergence (JSD) objective, Barlow-Twins, VICReg, and a combined BYOL-JSD objective -- across three architectures: O-Net, O-Net++, and a DINOv3-initialised O-Net. Each configuration is evaluated under two frozen-feature readouts that differ only in the form of their decision boundary: a linear probe and a non-linear XGBoost classifier fit only on the 24 labelled validation images. Our central finding is a consistent inversion between the two readouts: DINOv3 features are the weakest under linear probing but the strongest under a non-linear readout. A UMAP analysis of the learned feature space shows that DINOv3 fragments pixels into many small clusters in which the classes are locally interleaved, whereas the convolutional architectures (O-Net and O-Net++) embed them onto a single class-sorted manifold. Satellite-pretrained DINOv3 improves over natural-image initialisation across objectives, and our label-efficient DINOv3-ViT-L-Sat-O-Net-BYOL-JSD pipeline reaches 75.33 mDSC / 61.28 mIoU, outperforming standard machine learning baselines fit on the same 24 labelled images with the RGB pixel values used as features. We release CrevasseSeg to support label-efficient segmentation research in remote sensing.
Aug 14, 2026

Catching the Imposter: Self-Supervised Learning of Physical Coherence with Cross-Entity Feature Permutations

Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a discriminative pretext task that replaces subsets of an entity's features with real observations donated by another entity and trains the encoder to identify the swapped features. Because every donated value is individually plausible, the task can only be solved by learning cross-feature physical dependencies. We evaluate the proposed objectives on global ERA5-Land reanalysis data using 21 environmental variables and assess the learned representations on seven downstream tasks spanning climate classification, carbon flux estimation, and streamflow prediction. Our study includes, to our knowledge, the first systematic comparison of self-supervised objectives for land-surface modeling under a shared architecture and pre-training budget. We find that the most effective pretext task depends on the downstream task family rather than any single objective's superiority, and that imposter provides complementary information when combined with existing SSL objectives. These results suggest that physical coherence is a valuable new source of self-supervision for scientific foundation models.
Aug 8, 2026

Three Necessary Principles for Self-Supervised Visual Representation Learning

We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy. We formalize these as the observation, prediction, and regularization principles and prove (i) that combining observation and prediction without regularization admits the constant encoder as a global minimizer under negative-free alignment; (ii) that the two objectives are gradient-complementary and structurally non-conflicting at the encoder output; and (iii) that the momentum encoder converges to the same fixed point as the online encoder and provides no collapse guarantee at convergence. Contrastive alignment provides only self-limiting collapse resistance, formalized via an explicit gradient-decay argument. Dropping prediction withholds the spatial training signal by construction; dropping observation forfeits cross-view semantic invariance by construction; at the scale we study, no pair substitutes for the third. Every major self-supervised method is a special case of a single unified energy decomposition. We pair every theoretical claim with a controlled experiment, including a patch-retrieval evaluation for the spatial consequence of prediction.
Aug 7, 2026

Vernata: Self-Supervised Learning of LiDAR Point Representations

LiDAR serves as a primary sensing modality for robots operating in outdoor environments. However, the performance of deep learning models in this domain is severely limited by the scarcity of labeled data, a direct result of the high cost of 3D annotation. Self-supervised learning addresses this scarcity by learning general-purpose features from unlabeled data. In this work, we present a multi-modal, multi-teacher distillation framework for self-supervised learning on outdoor LiDAR point clouds. Building upon the Sonata architecture, we introduce Vernata, consisting of three extensions: sparse view augmentation to improve robustness against varying point densities, a memory bank mechanism to stabilize resource-constrained training, and cross-modal distillation utilizing dense, high-resolution 2D image features to enable fine-grained semantic guidance. We evaluate our method on the GrandTour, TartanGround, and Waymo datasets, as well as data collected from our own robotic platforms. Our experiments demonstrate a significant performance improvement over Sonata baselines, yielding mIoU scores of 54.7 on TartanGround (+5.9 points, +12.1%) and 57.1 on Waymo (+7.3 points, +14.7%). Finally, we show that the self-supervised approach maintains strong performance even in reduced-modality settings (lacking color or normals), achieving competitive mIoU scores of 49.4 and 50.2 on the respective datasets.
Aug 5, 2026

Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning

As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross-representation understanding across these modalities poses fundamental challenges for AI systems: the relationships across representations are inherently one-to-many, supervision is ambiguous and costly, and model optimization lacks a principled signal that is both direction-adaptive and representation-generalizable beyond task-specific objectives. We introduce CoCoEvolve to improve consistency across chart, table, and code representations. Instead of treating cross-representation mapping as a one-to-many problem, we define explicit one-to-one correspondences and optimize models using agreement between representations, without additional annotations. During training, CoCoEvolve@Train performs co-evolution across the chart-table-code cycle, while CoCoEvolve@Test applies the same consistency objective at inference time for test-time co-optimization. We also present CoCoEvolve@Eval, an evaluation suite covering all six cross-representation tasks. Across four benchmarks, CoCoEvolve improves performance in both training-time and test-time settings. Our project page: https://xhguo7.github.io/CoCoEvolve/.