Self-Supervised Visual Representation Learning

Optical Coherence Tomography (OCT) has become one of the most used imaging modality in ophthalmology. It provides high-resolution, non-invasive visualization of retinal microarchitecture. The automated analysis of OCT images through representation learning has emerged as a central research frontier. This has mainly been driven by the clinical need to process large acquisition volumes. The objective is to reduce the reliance on expert annotation, and improve diagnostic consistency across devices and populations. This survey provides a comprehensive and structured review of representation learning methods for retinal OCT image analysis. It covers the period from early deep learning approaches to the most recent developments in foundation models and vision-language systems. We organize the literature along a principled taxonomy of learning paradigms, encompassing supervised learning with CNN-based and transformer-based architectures, self-supervised and semi-supervised methods, generative approaches, as well as 3D volumetric modeling, multimodal representation learning, and large-scale pretrained foundation models. For each paradigm, we analyze the core methodological contributions, identify persistent limitations, and trace the connections between successive approaches. We further provide a structured overview of publicly available OCT datasets, discuss evaluation protocol considerations, and present a unified problem formulation that situates each learning paradigm within a common mathematical framework. Building on this analysis, we identify and discuss the most pressing open research directions emerging in the literature. This includes volumetric foundation model pretraining, uncertainty-aware representation learning, federated and privacy-preserving training, fairness and bias mitigation, concept-based interpretability,...

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.

Self-supervised learning methods learn high-quality visual representations, yet recent studies show that these representations often capture demographic biases present in the training data. Existing fairness-aware methods address this by redesigning the self-supervised objective itself, limiting portability across the rapidly evolving landscape of self-supervised learning (SSL) frameworks. We propose ProtoFair, a fairness-aware contrastive loss designed to work alongside existing SSL objectives without modifying them. ProtoFair leverages unsupervised prototype clustering to identify pseudo-counterfactual pairs: samples sharing the same cluster assignment but belonging to different sensitive groups. By pulling these content-matched, cross-group samples together in the embedding space, ProtoFair encourages the encoder to learn representations that are invariant to the sensitive attribute. The method requires only sensitive attribute annotations, no target labels, and integrates seamlessly with both SimCLR and SupCon. Experiments on CelebA and UTKFace demonstrate consistent fairness improvements while maintaining competitive accuracy.

Automated plant recognition plays a crucial role in biodiversity monitoring and conservation, yet current approaches rely heavily on supervised learning, which is limited by the availability of expert-labeled data. Self-supervised learning (SSL) offers a scalable alternative, but existing methods and training protocols are largely designed for coarse-grained visual tasks and may not transfer well to fine-grained domains such as plant species recognition. In this work, we investigate SSL for plant image representation learning. We show that commonly used augmentations in SSL pipelines - such as Gaussian blur, grayscale conversion, and solarization - are detrimental in the context of plant images, as they remove subtle discriminative cues essential for fine-grained recognition. We instead identify alternative transformations, including affine and posterization, that are better suited to this domain. We further demonstrate that training SimDINOv2 on the iNaturalist 2021 Plantae subset yields significantly stronger representations than training on ImageNet-1K, highlighting the importance of domain-specific data for SSL. Our findings are consistent across both ViT-Base and ViT-Large architectures. Moreover, our models achieve competitive performance and sometimes outperform strong supervised baselines Pl@ntCLEF and BioCLIP on downstream plant recognition tasks in few-shot settings. Overall, our results highlight the critical importance of domain-adapted augmentation strategies and dataset selection in self-supervised learning, and provide practical guidelines for building scalable models for biodiversity monitoring.

Modern self-supervised representation learning methods often relies on empirical heuristics that are not theoretically grounded. In this study we propose HyDeS, a theoretically grounded method based on multi-view mutual information maximization within an hyperspherical space using Shannon differential entropy with a non-parametric von Mises-Fisher density estimator. We show that HyDeS bias the trained model towards focusing on foreground features of the images and perform well on segmentation tasks such as VOC PASCAL, while it lags in fine-grained classification. We provide a detailed analysis of the induced latent space geometry and learning dynamics, that can be used for designing other theoretically grounded self-supervised learning methods.

Content-based image retrieval (CBIR) systems enable users to search images based on visual content instead of relying on metadata. The text domain has benefited from vector search of representations created with unsupervised methods such as BERT. However, modern self-supervised learning methods for vision are mostly not reported in CBIR-related literature, instead relying on supervised models or multi-modal methods that align text and vision. We evaluate how the representations learned by modern self-supervised learning methods for vision perform under typical retrieval stacks that leverage vector databases and nearest neighbor search. Our evaluation reveals that the latent space geometry impacts approximate nearest neighbor (ANN) indexing. Specifically, highly anisotropic representations with high skewness produced by several modern SSL methods degrade the performance of partition-based and hashing-based search, even if their own linear probe or K-NN accuracy is not affected. In contrast, representations with higher isotropy and local purity better satisfy the distance-based assumptions of ANN indexes, leading to improved semantic retrieval performance.

There has been growing interest in studying the complexity of Rectified Linear Unit (ReLU) based activation networks. Recent work investigates the evolution of the number of piecewise-linear partitions (linear regions) that are formed during training. However, current research is limited to examining the complexity of models trained in a supervised way. Self-Supervised Learning (SSL) differs in that it directly optimises the representation space using a loss function to enhance the model's performance across multiple downstream tasks. This study investigates the local distribution of linear regions produced by SSL models. We demonstrate that the evolution of linear regions correlates with the representation quality by utilising SplineCam to extract two-dimensional polytopes near the data distribution. We track the number, area, eccentricity, and boundaries of regions throughout training. The study compares supervised, contrastive, and self-distillation methods over two standard benchmark datasets, MNIST and FashionMNIST. The analysis of the experimental results shows that self-supervised methods create substantially fewer regions to achieve comparable accuracy to supervised models. Contrastive methods rapidly expand regions over time, whereas self-distillation methods tend to consolidate by merging neighbouring regions. Lastly, we can detect representation collapse early within the geometric space of linear regions. Our analysis suggests that polytopal metrics can serve as reliable indicators of representation quality and model performance.

We present Sapiens2, a model family of high-resolution transformers for human-centric vision focused on generalization, versatility, and high-fidelity outputs. Our model sizes range from 0.4 to 5 billion parameters, with native 1K resolution and hierarchical variants that support 4K. Sapiens2 substantially improves over its predecessor in both pretraining and post-training. First, to learn features that capture low-level details (for dense prediction) and high-level semantics (for zero-shot or few-label settings), we combine masked image reconstruction with self-distilled contrastive objectives. Our evaluations show that this unified pretraining objective is better suited for a wider range of downstream tasks. Second, along the data axis, we pretrain on a curated dataset of 1 billion high-quality human images and improve the quality and quantity of task annotations. Third, architecturally, we incorporate advances from frontier models that enable longer training schedules with improved stability. Our 4K models adopt windowed attention to reason over longer spatial context and are pretrained with 2K output resolution. Sapiens2 sets a new state-of-the-art and improves over the first generation on pose (+4 mAP), body-part segmentation (+24.3 mIoU), normal estimation (45.6% lower angular error) and extends to new tasks such as pointmap and albedo estimation. Code: https://github.com/facebookresearch/sapiens2

Self-supervised learning (SSL) is a standard approach for representation learning in aerial imagery. Existing methods enforce invariance between augmented views, which works well when augmentations preserve semantic content. However, aerial images are frequently degraded by haze, motion blur, rain, and occlusion that remove critical evidence. Enforcing alignment between a clean and a severely degraded view can introduce spurious structure into the latent space. This study proposes a training strategy and architectural modification to enhance SSL robustness to such corruptions. It introduces a per-sample, per-factor trust weight into the alignment objective, combined with the base contrastive loss as an additive residual. A stop-gradient is applied to the trust weight instead of a multiplicative gate. While a multiplicative gate is a natural choice, experiments show it impairs the backbone, whereas our additive-residual approach improves it. Using a 200-epoch protocol on a 210,000-image corpus, the method achieves the highest mean linear-probe accuracy among six backbones on EuroSAT, AID, and NWPU-RESISC45 (90.20% compared to 88.46% for SimCLR and 89.82% for VICReg). It yields the largest improvements under severe information-erasing corruptions on EuroSAT (+19.9 points on haze at s=5 over SimCLR). The method also demonstrates consistent gains of +1 to +3 points in Mahalanobis AUROC on a zero-shot cross-domain stress test using BDD100K weather splits. Two ablations (scalar uncertainty and cosine gate) indicate the additive-residual formulation is the primary source of these improvements. An evidential variant using Dempster-Shafer fusion introduces interpretable signals of conflict and ignorance. These findings offer a concrete design principle for uncertainty-aware SSL. Code is publicly available at https://github.com/WadiiBoulila/trust-ssl.

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.

This paper investigates the intrinsic geometrical features of highly similar objects and introduces a general self-supervised framework called the Geometric Attribute Exploration Network (GAEor), which is designed to address the ultra-fine-grained visual categorization (Ultra-FGVC) task in data-limited scenarios. Unlike prior work that often captures subtle yet critical distinctions, GAEor generates geometric attributes as novel alternative recognition cues. These attributes are determined by various details within the object, aligned with its geometric patterns, such as the intricate vein structures in soybean leaves. Crucially, each category exhibits distinct geometric descriptors that serve as powerful cues, even among objects with minimal visual variation -- a factor largely overlooked in recent research. GAEor discovers these geometric attributes by first amplifying geometry-relevant details via visual feedback from a backbone network, then embedding the relative polar coordinates of these details into the final representation. Extensive experiments demonstrate that GAEor significantly sets new state-of-the-art records in five widely-used Ultra-FGVC benchmarks.

Face Anti-Spoofing (FAS) remains challenging due to the requirement for robust domain generalization across unseen environments. While recent trends leverage Vision-Language Models (VLMs) for semantic supervision, these multimodal approaches often demand prohibitive computational resources and exhibit high inference latency. Furthermore, their efficacy is inherently limited by the quality of the underlying visual features. This paper revisits the potential of vision-only foundation models to establish a highly efficient and robust baseline for FAS. We conduct a systematic benchmarking of 15 pre-trained models, such as supervised CNNs, supervised ViTs, and self-supervised ViTs, under severe cross-domain scenarios including the MICO and Limited Source Domains (LSD) protocols. Our comprehensive analysis reveals that self-supervised vision models, particularly DINOv2 with Registers, significantly suppress attention artifacts and capture critical, fine-grained spoofing cues. Combined with Face Anti-Spoofing Data Augmentation (FAS-Aug), Patch-wise Data Augmentation (PDA) and Attention-weighted Patch Loss (APL), our proposed vision-only baseline achieves state-of-the-art performance in the MICO protocol. This baseline outperforms existing methods under the data-constrained LSD protocol while maintaining superior computational efficiency. This work provides a definitive vision-only baseline for FAS, demonstrating that optimized self-supervised vision transformers can serve as a backbone for both vision-only and future multimodal FAS systems. The project page is available at: https://gsisaoki.github.io/FAS-VFMbenchmark-CVPRW2026/ .

One of the dominant paradigms in self-supervised learning (SSL), illustrated by MoCo or DINO, aims to produce robust representations by capturing features that are insensitive to certain image transformations such as illumination, or geometric changes. This strategy is appropriate when the objective is to recognize objects independently of their appearance. However, it becomes counterproductive as soon as appearance itself constitutes the discriminative signal. In weather analysis, for example, rain streaks, snow granularity, atmospheric scattering, as well as reflections and halos, are not noise: they carry the essential information. In critical applications such as autonomous driving, ignoring these cues is risky, since grip and visibility depend directly on ground conditions and atmospheric conditions. We introduce ST-STORM, a hybrid SSL framework that treats appearance (style) as a semantic modality to be disentangled from content. Our architecture explicitly separates two latent streams, regulated by gating mechanisms. The Content branch aims at a stable semantic representation through a JEPA scheme coupled with a contrastive objective, promoting invariance to appearance variations. In parallel, the Style branch is constrained to capture appearance signatures (textures, contrasts, scattering) through feature prediction and reconstruction under an adversarial constraint. We evaluate ST-STORM on several tasks, including object classification (ImageNet-1K), fine-grained weather characterization, and melanoma detection (ISIC 2024 Challenge). The results show that the Style branch effectively isolates complex appearance phenomena (F1=97% on Multi-Weather and F1=94% on ISIC 2024 with 10% labeled data), without degrading the semantic performance (F1=80% on ImageNet-1K) of the Content branch, and improves the preservation of critical appearance

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 $F_1$ $\geq$ 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.

Neural radiance fields (NeRFs) have emerged as a prominent pre-training paradigm for vision-centric autonomous driving, which enhances 3D geometry and appearance understanding in a fully self-supervised manner. To apply NeRF-based pretraining to 3D perception models, recent approaches have simply applied NeRFs to volumetric features obtained from view transformation. However, coupling NeRFs with view transformation inherits conflicting priors; view transformation imposes discrete and rigid representations, whereas radiance fields assume continuous and adaptive functions. When these opposing assumptions are forced into a single pipeline, the misalignment surfaces as blurry and ambiguous 3D representations that ultimately limit 3D scene understanding. Moreover, the NeRF network for pre-training is discarded during downstream tasks, resulting in inefficient utilization of enhanced 3D representations through NeRF. In this paper, we propose a novel NeRF-Resembled Point-based 3D detector that can learn continuous 3D representation and thus avoid the misaligned priors from view transformation. NeRP3D preserves the pre-trained NeRF network regardless of the tasks, inheriting the principle of continuous 3D representation learning and leading to greater potentials for both scene reconstruction and detection tasks. Experiments on nuScenes dataset demonstrate that our proposed approach significantly improves previous state-of-the-art methods, outperforming not only pretext scene reconstruction tasks but also downstream detection tasks.

Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL). However, many of these models rely on architectures that offer limited interpretability, a critical issue in high-stakes domains such as medical imaging. We propose \model, a foundation model that is interpretable-by-design via a BagNet backbone whose small receptive fields generate class evidence maps that are faithful to the model's decision-making process. Additionally, \model{} incorporates a $2D$ projection layer during pretraining that enables direct visualization of the representation space, providing a dataset-level view of the learned structure including meaningful clinical clusters as well as potential spurious correlations. We trained \model{} on over 800,000 color fundus photographs from various sources to learn generalizable representations for different downstream tasks. Our model achieves performance comparable to RETFound, which has $16\times$ more parameters, while providing interpretable predictions on out-of-distribution data. These results suggest that large-scale SSL pretraining paired with inherent interpretability can lead to robust representations for retinal imaging. Code and pretrained models are available at www.anonymous.4open.science/dual-IFM.

Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties. However, their alignment with human object perception remains poorly understood. Here, we introduce a behavioral benchmark in which participants make same/different object judgments for dot pairs on naturalistic scenes, scaling up a classical psychophysics paradigm to over 1000 trials. We test a diverse set of vision models using a simple readout from their representations to predict subjects' reaction times. We observe a steady improvement across model generations, with both architecture and training objective contributing to alignment, and transformer-based models trained with the DINO self-supervised objective showing the strongest performance. To investigate the source of this improvement, we propose a novel metric to quantify the object-centric component of representations by measuring patch similarity within and between objects. Across models, stronger object-centric structure predicts human segmentation behavior more accurately. We further show that matching the Gram matrix of supervised transformer models, capturing similarity structure across image patches, with that of a self-supervised model through distillation improves their alignment with human behavior, converging with the prior finding that Gram anchoring improves DINOv3's feature quality. Together, these results demonstrate that self-supervised vision models capture object structure in a behaviorally human-like manner, and that Gram matrix structure plays a role in driving perceptual alignment.

When humans learn new manipulation skills, they are able to generalize these skills to new contexts and environments. In particular, when learning, humans can easily separate task-relevant aspects of the environment (e.g., object location) and distractors (e.g., the table color). Ideally, robot policies should be able to learn similar, generalizable representations, but instead they often fail under small environment shifts such as changes in lighting, object instance, or initial configuration. In this paper, we propose a self-supervised method that learns a mask which, when multiplied by the observed image features, attempts to transform these features to retain only those which are relevant to the task. Our method --- which we call TransMASK --- can be combined with a variety of imitation learning frameworks (such as diffusion policies) without any additional labels or alterations to the loss function. By introducing a learned mask to the network during training, we aim to induce competitive pressure among the image features during training to force the policy to only attend to features which are consistently task-relevant. We find empirically that our masks are interpretable and can reject known spurious features such as the position of distractor objects or the background color. When compared to other representation learning methods for imitation learning, we find that TransMASK results in policies that are more robust to distribution shifts for irrelevant features, achieving at least 30 % improvement over the baselines when tested on out-of-distribution environments. See our project website: https://transmask.github.io/TransMASK/

The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting considerable attention for its efficient handling of long-sequence tasks. Its inherent causal structure makes it particularly well suited for autoregressive pretraining. However, existing autoregressive pretraining methods in vision are largely limited to short-sequence settings and may not fully use Mamba's capacity to model longer contexts. To investigate this setting, we introduce SeparaTors for AutoRegressive pretraining (STAR), a new autoregressive pretraining method for Vision Mamba that explicitly marks the boundaries between different images. STAR increases the patch-token sequence length from 144 to 640 by packing four images and four separator clusters. This is approximately $4.4\times$ the ARM patch-token sequence length. The increase is achieved without changing the resolution of any individual image: we use $192\times192$ inputs for autoregressive pretraining and $224\times224$ inputs for downstream classification fine-tuning. With this long-sequence pretraining scheme, STAR-B achieves 83.5% EMA top-1 accuracy on ImageNet-1K after 1,600 epochs of pretraining. The learned representation also transfers beyond in-distribution classification: compared with ARM, STAR-B improves COCO box AP from 46.11 to 46.84 and mask AP from 40.74 to 41.45, while raising the mean top-1 accuracy across five ImageNet robustness benchmarks from 55.1% to 56.8%. Under the evaluated four-image setting, these results indicate that separator-based long-sequence pretraining improves recognition robustness and dense visual prediction relative to ARM.

Ultrasound (US) imaging poses unique challenges for representation learning due to its inherently noisy acquisition process. The low signal-to-noise ratio and stochastic speckle patterns hinder standard self-supervised learning methods relying on a pixel-level reconstruction objective. Joint-Embedding Predictive Architectures (JEPAs) address this drawback by predicting masked latent representations rather than raw pixels. However, standard approaches depend on hyperparameter-brittle and computationally expensive online teachers updated via exponential moving average. We propose US-JEPA, a self-supervised framework that adopts the Static-teacher Asymmetric Latent Training (SALT) objective. By using a frozen, domain-specific teacher to provide stable latent targets, US-JEPA decouples student-teacher optimization and pushes the student to expand upon the semantic priors of the teacher. In addition, we provide the first rigorous comparison of all publicly available state-of-the-art ultrasound foundation models on UltraBench, a public dataset benchmark spanning multiple organs and pathological conditions. Under linear probing for diverse classification tasks, US-JEPA achieves performance competitive with or superior to domain-specific and universal vision foundation model baselines. Our results demonstrate that masked latent prediction provides a stable and efficient path toward robust ultrasound representations.

A central problem in self-supervised learning is preventing representation collapse. Most methods avoid it through global mechanisms, such as contrastive expansion, variance constraints, decorrelating dimensions, or enforcing certain output distributions. In this work, we study a different design: short-range repulsion. We introduce Hypersolid, a self-supervised objective that combines view alignment with local collision avoidance. Our method induces a latent geometry of compact, semantically aligned neighborhoods with low anisotropy. This geometry is especially effective for unsupervised clustering and fine-grained separation, although it comes at the cost of weaker transferability.

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures yet struggle with high-level semantic context. We argue that these paradigms are fundamentally complementary and can be integrated into a principled multi-task framework, further enhanced by dense spatial supervision. We introduce MTV, a multi-task visual pretraining framework that jointly optimizes a shared backbone across vision-language contrastive, self-supervised, and dense spatial objectives. To mitigate the need for manual annotations, we leverage high-capacity "expert" models--such as Depth Anything V2 and OWLv2--to synthesize dense, structured pseudo-labels at scale. Beyond the framework, we provide a systematic investigation into the mechanics of multi-task visual learning, analyzing: (i) the individual and marginal gain of each objective, (ii) task synergies versus interference, and (iii) scaling behavior across varying data and model scales. Our results demonstrate that MTV achieves "best-of-both-worlds" performance, significantly enhancing fine-grained spatial reasoning without compromising global semantic understanding. Our findings suggest that multi-task learning, fueled by high-quality pseudo-supervision, is a scalable path toward more general visual encoders.

Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs), theoretically allowing them to maintain high-dimensional representations throughout all layers. However, recent observations suggest ViTs often spontaneously manifest a "U-shaped" entropy profile-compressing information in middle layers before expanding it for the final classification. In this work, we demonstrate that this "Inductive Bottleneck" is not an architectural artifact, but a data-dependent adaptation. By analyzing the layer-wise Effective Encoding Dimension (EED) of DINO-trained ViTs across datasets of varying compositional complexity (UC Merced, Tiny ImageNet, and CIFAR-100), we show that the depth of the bottleneck correlates strongly with the semantic abstraction required by the task. We find that while texture-heavy datasets preserve high-rank representations throughout, object-centric datasets drive the network to dampen high-frequency information in middle layers, effectively "learning" a bottleneck to isolate semantic features.

Natural scenes are complex arrangements of objects, surfaces, and backgrounds. For the brain's visual system to effectively operate, it needs to extract not only what objects are present, but also their spatial and semantic relations. We hypothesize that such structures may be learned, in a self-supervised fashion, by exploiting temporal regularities of natural active vision: each fixation reveals a glimpse that is related to the previous one via co-occurrence and saccade-conditioned spatial regularities. We instantiate this idea with Glimpse Prediction Networks (GPNs), recurrent models trained to predict the embedding of the next glimpse along human-like scanpaths. GPNs are shown to successfully extract complex scene information, including object co-occurrences and spatial object arrangements, and integrate information across glimpses. Importantly, GPN representations align strongly with human fMRI responses in mid and higher-level visual cortex and match, often outperform, alternative state-of-the-art ANN models, establishing next-glimpse-prediction as a biologically plausible route towards brain-aligned scene representations.

While foundation models have emerged as general-purpose visual backbones, their representations are primarily optimized for semantics and lack explicit modeling of physical factors, such as reflectance, hindering their efficacy in tasks requiring explicit material reasoning. We introduce $Φ$eat$, a novel material-grounded visual backbone that encourages a representation sensitive to material identity, including reflectance and mesostructure. Instead of relying on generic data augmentations, we pretrain our model by contrasting observations of the same material under controlled variations in lighting and geometry. This encourages invariance to extrinsic factors while preserving sensitivity to intrinsic material properties. We show that the resulting representation provides strong priors for material-centric tasks, including feature-based material selection and classification. Our results demonstrate that physically inspired weak supervision is an effective strategy for learning representations tailored to material perception.

The integration of Large Language Model (LLM) blocks with Vision Transformers (ViTs) holds significant promise for vision-only tasks by leveraging the rich semantic knowledge and reasoning capabilities of LLMs. However, a fundamental challenge lies in the inherent modality mismatch between the text-centric pre-training of LLMs and the vision-centric training of ViTs. Direct fusion often fails to fully exploit the LLM's potential and suffers from unstable finetuning. Consequently, prior works typically keep LLM blocks frozen while learning only the vision components. To address these challenges, we introduce Language-Adapted Vision Enhancer (LAVIE), a novel framework that bridges this modality gap through a synergistic pre-training strategy. LAVIE co-adapts a ViT backbone and an LLM fusion block by (1) employing Masked Auto-Encoding (MAE) to pre-train the ViT for richer visual representations, and (2) concurrently training Low-Rank Adaptation (LoRA) layers within the LLM block using the same MAE objective. This joint optimization guides the ViT to produce LLM-aligned features and the LLM to effectively interpret visual information. We demonstrate through extensive experiments that LAVIE significantly improves performance in various downstream vision tasks, offering an effective and efficient way to enhance visual understanding using frozen LLM knowledge. Code is available at https://github.com/selimkuzucu/LAVIE

Most self-supervised learning objectives defend against collapse but leave the target representation law unspecified. We formulate representation learning as Distribution Matching (DM), learning an augmentation-invariant encoder whose induced law matches an explicit geometric reference. The reference law specifies what the learned representation distribution should look like, whereas a separately chosen discrepancy determines how deviations from this target are measured; here we use Mallows distance. The DM framework reveals a directional inverse: generative learning maps a tractable reference to data, whereas representation learning maps data to a designed reference law. We connect the population objective to class-centre separation and classification error and prove a non-asymptotic neural-sieve guarantee. Simulations and image benchmarks show manifold rectification, fine-grained structure and transfer across label spaces.

Contrastive learning relies on informative negatives to shape the representation space, yet obtaining hard negatives is costly, often requiring large batch sizes or extensive memory banks. We propose SynCo (Synthetic negatives in Contrastive learning), an approach that synthesizes hard negatives directly in the representation space from cached queue embeddings, with no additional forward passes or input-space processing. We find that six lightweight synthesis strategies, exhaustively covering the geometric, stochastic, and adversarial perturbation families, consistently improve learned representations at negligible computational cost. Although applicable to any InfoNCE-based contrastive objective, we demonstrate SynCo within the MoCo framework. On ImageNet ILSVRC-2012 linear evaluation at 200 epochs, SynCo yields improvements of +0.4% over MoCo-v2 and +1.0% over MoCHi. Unlike MoCHi, which degrades at extended pretraining schedules (underperforming MoCo-v2 by 2.4% at 800 epochs), SynCo does not: with a simple synthetic negative schedule, performance improves by +0.5% over MoCo-v2 at 800 epochs. SynCo also transfers well to a range of downstream tasks.

We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in areas like task planning and learning from demonstration. We identify and explore two different aspects of the concept of CATE: Action Selection (AS) and Effect-Affinity Assessment (EAA), where video understanding models connect actions and effects at semantic and fine-grained levels, respectively. We design various baseline models for AS and EAA. Despite the intuitive nature of the task, we observe that models struggle, and humans outperform them by a large margin. Our experiments show that in solving AS and EAA, models learn intuitive properties like object tracking and pose encoding without explicit supervision. We demonstrate that CATE can be an effective self-supervised task for learning video representations from unlabeled videos. The study aims to showcase the fundamental nature and versatility of CATE, with the hope of inspiring advanced formulations and models.

Maintaining proper form while exercising is important for preventing injuries and maximizing muscle mass gains. Detecting errors in workout form naturally requires estimating human's body pose. However, off-the-shelf pose estimators struggle to perform well on the videos recorded in gym scenarios due to factors such as camera angles, occlusion from gym equipment, illumination, and clothing. To aggravate the problem, the errors to be detected in the workouts are very subtle. To that end, we propose to learn exercise-oriented image and video representations from unlabeled samples such that a small dataset annotated by experts suffices for supervised error detection. In particular, our domain knowledge-informed self-supervised approaches (pose contrastive learning and motion disentangling) exploit the harmonic motion of the exercise actions, and capitalize on the large variances in camera angles, clothes, and illumination to learn powerful representations. To facilitate our self-supervised pretraining, and supervised finetuning, we curated a new exercise dataset, Fitness-AQA (https://github.com/ParitoshParmar/Fitness-AQA), comprising of three exercises: BackSquat, BarbellRow, and OverheadPress. It has been annotated by expert trainers for multiple crucial and typically occurring exercise errors. Experimental results show that our self-supervised representations outperform off-the-shelf 2D- and 3D-pose estimators and several other baselines. We also show that our approaches can be applied to other domains/tasks such as pose estimation and dive quality assessment.