Visual Representation Learning

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 367% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 147

Jul 6, 2026cs.CV

Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension

Referring expression comprehension (REC) aims to localize the object in an image described by natural language. In Weakly supervised REC (WREC), existing approaches primarily operate on anchor-level visual representations. Even when enriched with auxiliary cues, relational interactions remain implicitly encoded within individual anchor features. The resulting visual representation remains flat and unary-only, limiting its ability to align with the structured nature of language. In this work, we propose a Structured Visual Compositional Representation (SVCR) learning framework for WREC. Rather than implicitly encoding relations within unary anchors, the proposed SVCR explicitly models both unary object embeddings and pairwise relational embeddings, forming a structured visual representation space. We further introduce a compositional alignment mechanism that matches unary and pairwise visual representations with their corresponding textual embeddings in a unified manner, enabling compositional visual-textual matching under weak supervision. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg show that the proposed SVCR achieves state-of-the-art performance. These results demonstrate the effectiveness of explicit structured visual representations and visual-textual alignment for WREC.

Lian Xu, Mohammed Bennamoun, Farid Boussaid +3

The University of Western Australia · Murdoch University · Sun Yat-sen University +1

Visual Representation Learning Vision-Language Grounding Vision-Language Alignment

Jul 3, 2026cs.CV

Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation

Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently understood. In this work, we systematically analyze MAs in representative DiTs and find that they are spatially distributed across image tokens while concentrated in a small set of fixed feature dimensions. We further show that these dimensions are closely aligned with AdaLN residual scaling factors and are primarily modulated by the denoising timestep rather than text conditions. This structure leads to two task-dependent effects: for generation, MAs are critical for fine-grained detail synthesis while having limited influence on global semantics; for understanding, their shared high-magnitude directions make raw DiT features overly similar across spatial tokens and weaken dense feature discrimination. Based on these findings, we introduce Eliciting Massive Activation (EMA), a training-free framework that leverages Massive Activations (MAs) as a unified modulation signal to improve both generative and representational capabilities of DiTs. For generation, EMA proposes MA-driven Detail G}uidance (DG), which suppresses MA dimensions to construct a detail-deficient counterfactual prediction and guides sampling toward finer visual details. DG further supports efficient partial-forward inference, integration with classifier-free guidance, and token-level Local DG for refining selected image regions. For understanding, EMA introduces MA-modulated REPresentation extraction (MREP), which uses pretrained AdaLN channel-wise modulation to reduce MA directional dominance and concatenates spatially normalized MA maps to preserve useful spatial structure. Extensive experiments demonstrate that EMA consistently improves both the generation quality and representation capability of DiTs.

Chaofan Gan, Zicheng Zhao, Yuanpeng Tu +6

Shanghai Jiao Tong University, Shanghai, China · The University of Hong Kong, Hong Kong, China · Monash University, Melbourne, Australia +2

Visual Representation Learning Diffusion Transformer Diffusion Guidance Diffusion-Based Image Generation

Jul 2, 2026cs.CV

Transformer Geometry Observatory TGO-II: Representational Similarity Observatory

While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood. Existing analyses primarily focus on attention mechanisms and downstream performance, leaving the evolution of representation geometry largely unexplored. In this work, we present Transformer Geometry Observatory-II (TGO-II), a representation geometry analysis framework designed to investigate how Transformer representations evolve during supervised training. TGO-II analyzes Vision Transformer (ViT-Small/16) representations using Centered Kernel Alignment (CKA), Singular Vector Canonical Correlation Analysis (SVCCA), Two-Nearest Neighbor Intrinsic Dimensionality (TwoNN-ID), and token covariance analysis. Our experiments reveal three key observations. First, both CKA and SVCCA progressively decrease throughout training, indicating increasing representational specialization across Transformer layers. Second, intrinsic dimensionality consistently increases before stabilizing, suggesting progressive expansion of the representation manifold into a larger set of locally accessible degrees of freedom. Third, token covariance and coupling analyses demonstrate that strong token interaction structure persists throughout training, challenging the hypothesis that increasing representational complexity arises primarily from progressive token independence. These findings suggest that representation complexity and layer specialization emerge simultaneously during training. Manifold expansion appears to occur without token decoupling. Together, these observations motivate a new hypothesis in which Vision Transformers increase representational complexity through progressively richer transformations while preserving strong token interaction structure during learning.

Kaustubh Kapil, Kishor P. Upla

Department of Electronics Engineering Sardar Vallabhai National Institute of Technology (SVNIT), Surat, India

Intrinsic Dimensionality Representational Similarity Analysis Neural Representation Geometry Visual Representation Learning Vision Transformer

Jul 1, 2026cs.CV

LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives

Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods. At the same time, the role of vision-language encoders has shifted: they are increasingly deployed not as zero-shot classifiers but as the frozen visual backbone of vision-language models and dense prediction systems, which consume the full grid of patch tokens rather than a single pooled embedding. We introduce LeVLJEPA, the first fully non-contrastive end-to-end vision-language pretraining method. LeVLJEPA learns through cross-modal prediction with stop-gradient targets and per-modality distributional regularization, without negatives, temperature, momentum encoder, or teacher-student schedule, and trains stably at large scale. We find that the resulting encoder provides markedly stronger dense semantic features for downstream use: as a frozen vision-language-model backbone, LeVLJEPA is the strongest of the evaluated encoders across GQA, VQAv2, and POPE under two distinct language models, and outperforms contrastive baselines on semantic segmentation, while remaining on par on global readouts such as linear probing. These results establish non-contrastive pretraining as an effective means of producing dense semantic vision features.

Lukas Kuhn, Giuseppe Serra, Randall Balestriero +1

German Cancer Research Center · German Cancer Consortium · Brown University +1

Visual Representation Learning Vision-Language Pretraining

Jul 1, 2026cs.CV

Identifying Latent Concepts and Structures for Generalized Category Discovery

Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings. However, current approaches primarily focus on designing clustering objectives, often overlooking a critical bottleneck: standard vision backbones yield high-rank, entangled token representations that are ill-suited for unsupervised discovery of latent concepts and structures. In this paper, we propose Compositional Primitive Fields (CPF-GCD), a novel representation learning framework that reshapes the feature space to make such latent structure identifiable by enforcing a low-rank compositional organization. Our core hypothesis is that all categories, whether known or novel, can be expressed as compositions and spatial arrangements of a finite set of learnable visual primitives that capture reusable concepts. CPF instantiates this geometric constraint via a spatial field mechanism. Inserted between the backbone and the head, it rewrites noisy patch tokens through low-rank primitive mixtures, effectively decomposing images into reusable atomic parts and their spatial layouts. By explicitly modeling the spatial distribution of primitives, CPF enables novel categories to emerge naturally as new activation patterns over a shared vocabulary. This shifts the focus of representation from merely partitioning global embeddings to constructing a structured and separable primitive field. Extensive experiments demonstrate that CPF serves as a generic, plug-and-play module that consistently boosts performance across diverse GCD baselines, validating that identifying and leveraging low-rank compositional structure is a crucial inductive bias for open-world recognition.

Boyang Dai, Chaoqi Chen, Yizhou Yu

1The University of Hong Kong · 2Shenzhen University

Representation Learning Visual Representation Learning Compositional Representation Learning Generalized Category Discovery

Jun 29, 2026cs.CV

Cross-Resolution Semantic Transfer for Robust Text-to-Image Retrieval in Low-Resolution Surveillance

Text-to-image person re-identification (TIPR) retrieves target persons using natural language descriptions. However, existing methods largely overlook resolution variance in real-world surveillance. They characterize cross-resolution TIPR through two coupled failure modes: Evidence Reliability Collapse (ERC), where degraded visual tokens become unreliable for grounding fine-grained text, and Ranking Distribution Drift (RDD), where mixed-resolution galleries distort similarity neighborhoods and destabilize retrieval rankings. To address this challenge, we propose Cross-Resolution Semantic Transfer (CRST), a CLIP-style framework with three modules: resolution-conditioned reasoning, text-guided refinement and CR-RDA. Resolution-conditioned reasoning estimates token reliability to suppress corrupted evidence. Text-guided refinement injects semantic priors to recover discriminative cues. CR-RDA transfers HR neighborhood geometry to stabilize LR ranking under mixed resolutions. Experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid show that CRST improves ultra-low-resolution Rank-1 and mAP on average by 5.7% and 5.3%, while stabilizing mixed-resolution retrieval without sacrificing high-resolution accuracy.The code will be made publicly available.

Wenjie Qian, Bin Yang, Xiao Wang +4

𝑎School of Computer Science and Technology, Wuhan University of Science and Technology · 𝑏School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University · 𝑐Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology

Visual Representation Learning Cross-Modal Retrieval Person Re-Identification

Jun 25, 2026cs.CV

ViQ: Text-Aligned Visual Quantized Representations at Any Resolution

A unified representation for text and vision is a natural pursuit, as it enables simpler multimodal modeling and more efficient training. However, representing images as discrete signals in the same way as text inevitably introduces severe information loss. Existing work struggles to balance low-level details and high-level semantics in discrete representations: reconstruction-oriented representations often lack semantic information, whereas semantically stronger features typically suffer from severe loss of detail. We present ViQ, a Visual Quantized Representations framework, which is designed to balance semantics and details in discrete representations while supporting inputs at native resolutions, thereby enabling it to serve as a unified and general discrete representation for arbitrary visual inputs. Our approach structures quantization learning into two stages: text-aligned pre-training and feature discretization. With text-aligned pre-training, we enhance the visual encoder semantic-rich supervision from the pretrained language model and enable it to process native-resolution visual inputs. During discretization, we propose a proximal representation learning strategy to progressively compact the feature space, along with a position-aware head-wise quantization mechanism that enables flexible processing of arbitrary resolutions. Extensive experiments on multimodal tasks demonstrate that ViQ achieves competitive performance compared to state-of-the-art multimodal vision encoders with continuous and high-dimensional visual features, while maintaining high precision in low-level reconstruction. We also show that multimodal training with visual quantized representations largely improves efficiency, yielding up to 20%-70% acceleration with different base LLMs and training recipes.

Xumin Yu, Zuyan Liu, Zhenyu Yang +5

Tencent HY Vision Team · Tsinghua University · Institute of Automation, CAS +1

Visual Representation Learning Multimodal Pretraining Vision-Language Alignment Visual Token Compression Multimodal Understanding

Jun 24, 2026cs.CV

Meta-learning as a principle for human-like visual representations

The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual representations with unprecedented success, a large discrepancy remains. We propose one reason: these networks optimise a single fixed objective, whereas human representations must support open-ended tasks. We hypothesise this flexibility arises from meta-learning (learning to learn), a pressure shaping representations to acquire new tasks from few observations. To test this, we train a sequence model, without any supervision from human data, across thousands of semantically rich tasks mapping images to high-level concepts. Compared to their pretrained base encoders, meta-learned representations better predict human similarity judgements, semantic rule learning, and high-level visual cortex. Behavioural gains depend on disentangled, high-level task distributions, while brain alignment is driven primarily by the learning-to-learn pressure. Our results suggest the flexibility of human visual representations reflects the functional demand to learn new semantic relationships on the fly.

Can Demircan, Marcel Binz, Alireza Modirshanechi +1

Helmholtz Munich, Munich, Germany · Max Planck Institute for Biological Cybernetics, Tübingen, Germany

Visual Representation Learning Meta-Learning

Jun 23, 2026cs.LG

Semantic Allocation in Ordered Bottlenecks: Predictive Residual Inference for Visual Representation Learning

Ordered bottlenecks aim to provide utility at flexible budgets by assigning coarse information to early tokens and task-relevant detail to later ones. Prior work, including tail dropping (TD), typically enforces ordering by means of a masking-based ordering pressure (MBOP): Late tokens are masked more frequently than early tokens and are therefore encouraged to store less essential fine details. We introduce predictive residual inference for ordered representations (PRIOR), a framework designed to address inherent weaknesses of MBOP. MBOP is prone to weak late-token utility because it lacks an explicit refinement objective and uses gradient exposure as a proxy for importance. Furthermore, representations may become particularly brittle in optimization-sensitive settings, such as when using discrete or quantized token representations. PRIOR replaces activation-rate control with log2-scaled levels and level-wise predictors. These predictors separate already explained from unexplained information, focusing each level on residual error. We compare PRIOR against MBOP-TD and independent tail-biased dropout (MBOP-ITD) in contrastive learning and image reconstruction tasks. Unlike the baselines, PRIOR learns well-ordered representations across experiments: low budgets provide coarse descriptors, while high budgets add refinements. Simultaneously, full-budget performance with PRIOR is higher in all but one experimental setting, where performance remains comparable. MBOP baselines are severely limited in discrete and quantized settings, while PRIOR approaches the performance of continuous counterparts. Taken together, these findings establish PRIOR as an effective framework for ordered representation learning.

Erik Ayari, Manuel Traub, Martin V. Butz

Neuro-Cognitive Modeling Group, University of Tübingen, Tübingen, Germany

Representation Learning Visual Representation Learning Residual Learning Predictive Representation Learning

Jun 23, 2026cs.LG

Learning Diachronic Representations of Ancient Greek Letterforms

Learning representations that remain robust across centuries of variation in handwriting is a key challenge in diachronic representation learning. Taking one of the longest continuously used writing systems, ancient Greek, as a case study, we introduce three datasets for diachronic representation learning: Hell-Char, a curated training set spanning the 3rd-1st centuries BCE, and two evaluation sets, PaLit-Char (2nd-5th c. CE) and Med-Char (9th-14th c. CE). To address the challenges of symbolic variation, scarce data, and systematic degradation, we propose: a similarity-weighted supervised contrastive loss that biases embeddings using dynamically estimated inter-class similarities, and a lacuna-driven augmentation scheme that simulates realistic manuscript corruptions. Trained with these strategies, both a lightweight CNN and a pretrained ResNet achieve strong recognition performance and produce embeddings that more coherently separate character classes than PCA or generic pretrained models. These embeddings enable clustering, identification of stylistic subgroups, and construction of prototype images that visualize diachronic evolution and transitional letterforms. Our results demonstrate that respecting intrinsic inter-letter relationships and augmenting with domain-informed corruptions yield robust, interpretable representations, offering a transferable paradigm for representation learning under scarce, temporally evolving, and noisy conditions. Code and data available at: https://github.com/ipavlopoulos/diachronic-greek-letterforms.

John Pavlopoulos, Spyros Barbakos, Lavinia Ferretti +7

Athens University of Economics and Business, Greece · Archimedes, Athena Research Center, Greece · Department of Computer and Systems Sciences, Stockholm University, Sweden +5

Representation Learning Visual Representation Learning Optical Character Recognition Supervised Contrastive Learning

Jun 21, 2026cs.CV

Learning Entropy Signature for Image Representation and Classification

Learning Entropy (LE) has recently been extended to image analysis through Spatial Learning Entropy Maps (SLEMs), which are two-dimensional LE distributions that highlight unusually high learning activity across an image. Unlike conventional image descriptors, SLEMs are generated by incremental, sample-wise learning of a pretrained feedforward MLP network, where local pixel neighborhoods are presented sequentially in a fixed spatial order to predict the corresponding central pixels. Consequently, the learning activity at each image location depends not only on its local structure but also on the knowledge acquired from previously processed locations. This paper introduces Learning Entropy Signatures (LES), an image descriptor derived from SLEM using the K largest LE locations. LES captures the spatial organization of learning-relevant image structures and provides a compact representation of image content based on learning weight behavior. Experimental evaluation on image classification tasks shows that a relatively small number of K largest LE locations preserve substantial discriminative information. The results indicate a close relationship between the learning of neural weights and information relevance, extending the role of Learning Entropy from time series to images and, within images, from structural point extraction to compact image representation and classification.

Jan Glaser, Ivo Bukovsky, Noriyasu Homma +1

Dpt. of Applied Mathematics Czech Technical University in Prague Prague, Czech Republic · Dpt. of Computer Science University of South Bohemia in Ceske Budejovice Ceske Budejovice, Czech Republic · Dpt. of Radiological Imaging and Informatics Tohoku University Graduate School of Medicine Sendai, Japan

Visual Representation Learning Image Classification

Jun 19, 2026cs.RO

A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world

Trained policies for real-world robotics rely on computer vision components, typically in the form of pre-trained visual encoders. These encoders are an essential component and it has been shown that their power does not emerge from training on robotics downstream losses alone. Pre-training with auxiliary losses in the form of computer-vision pre-text tasks is a defining factor and heavily conditions agent performance in robotics tasks. In this unprecedented large-scale study, we ran 966 navigation episodes of static point goal navigation in a real-world building for 24km and asked which components really matter for the computer vision aspects of robotics: we evaluate state-of-the art visual encoders in realistic conditions. We explore the usefulness of heterogeneous multi-teacher distillation leading to encoders with multiple different and complementary skills. We investigate how much information from these encoders is necessary for robotics by bottlenecking them in a principled and spatially useful way and we show that this leads to the emergence of interpretable features linked to affordances. We also argue that training policies on RGB data alone does not lead to an optimal usage of visual features and show this by finetuning policies pre-trained on privileged information. All in all, we paint a more complete picture of what aspects of computer vision are relevant for real-world navigation.

Steeven Janny, Leonid Antsfeld, Christian Wolf

NaverLabs Europe, Grenoble, France

Visual Representation Learning Robot Navigation Vision Transformer Knowledge Distillation

Jun 17, 2026cs.CV

Language-Instructed Vision Embeddings for Controllable and Generalizable Perception

Vision foundation models are typically trained as static feature extractors, placing the burden of task adaptation onto large downstream models. We propose an alternative paradigm: instead of solely feeding visual features into language models, we use language itself to dynamically guide the vision encoder. Our method, Language-Instructed Vision Embeddings (LIVE), leverages language as high-level guidance to produce task-centric embeddings at inference time, removing the need for task-specific retraining. This enables the encoder to focus on contextually relevant aspects of the input, yielding more controllable and generalizable representations. Empirically, LIVE reduces visual hallucinations (+34 points on MMVP), surpasses vision-language models with orders of magnitude more parameters on visual question answering, and generalizes to unseen instructions and tasks -- offering a direct path toward adaptive, instruction-driven visual intelligence.

Chengzhi Mao, Xudong Lin, Wen-Sheng Chu

Google

Visual Representation Learning Vision Foundation Model Adaptation VLM Hallucination Mitigation

Jun 17, 2026cs.CV

LARE: Low-Attention Region Encoding for Text-Image Retrieval

Image retrieval in crowded scenes is particularly challenging due to the salience bias of conventional visual encoders, which tend to focus on dominant objects while neglecting low-attention regions that are often crucial for fine-grained retrieval. We propose LARE (Low-Attention Region Encoding), a framework that explicitly models these overlooked regions. LARE adopts a dual-encoding strategy that encodes low-attention regions of an image and the full image in parallel, leading to more diverse and informative image embeddings. To evaluate image retrieval performance in challenging crowded scenes, we introduce Dense-Set, a challenging subset derived from COCO and Flickr30K. In this subset, images are re-captioned to provide richer descriptions of low-attention or previously overlooked regions. This dataset highlights the limitations of existing retrieval models and enables a more rigorous evaluation under densely crowded scene conditions. Experimental results demonstrate that the proposed framework improves retrieval performance by preserving subtle, non-dominant visual cues within the shared latent space.

Abdulmalik Alquwayfili, Faisal Almeshal, Jumanah Almajnouni +8

Saudi Data and Artificial Intelligence Authority (SDAIA), Riyadh, Saudi Arabia.

Visual Representation Learning Fine-Grained Image Retrieval Image-Text Retrieval Vision-Language Retrieval Fine-Grained Visual Perception

Jun 15, 2026cs.RO

Contrastive Action-Image Pre-training for Visuomotor Control

Existing vision encoders for robotics face a fundamental bottleneck: robotic datasets lack the scale necessary for large-scale pre-training. Prior work circumvents this data scarcity by turning to internet-scale image and language data or egocentric human video. While these models show promise, neither paradigm learns from paired vision and action data, which downstream visuomotor control policies require. However, robot trajectories, the most direct source of this paired signal, are not available at pre-training scale, motivating us to extract action signals from abundant human video instead. To this end, we introduce CAIP (Contrastive Action-Image Pre-training), a vision encoder that treats human hand poses from large-scale egocentric video as a proxy for end-effector actions. By extracting 3D hand keypoints, a representation that aligns naturally with downstream robot action spaces, CAIP learns a unified action-image representation through a contrastive objective. Leveraging 32,041 hours of egocentric human video and only 88 hours of robotic manipulation data, CAIP outperforms state-of-the-art vision encoders including DINOv2, SigLIP, MVP, and R3M. Evaluated on a challenging real-world dexterous manipulation setup using Dexmate Vega and Sharpa Wave hands, CAIP yields performance gains of more than 30% on tasks involving folding, pouring, and fine-grained manipulation. Our results show that our method of contrastive action-centric pre-training yields a scalable path to achieving robust visual representations better suited for physical interaction.

Yuvan Sharma, Dantong Niu, Anirudh Pai +16

1UC Berkeley · 2NVIDIA · 3Sapienza University of Rome +2

Contrastive Learning Visual Representation Learning Visuomotor Policy Learning Robotic Manipulation

Jun 15, 2026cs.CV

The Importance of Phase in Neural Representations: An Internal Oppenheim-Lim Test of Image Classifiers

Oppenheim and Lim (1981) showed that natural images stay recognizable when reconstructed from their Fourier phase alone, while the magnitude carries little of their identity. We ask whether trained image classifiers reproduce this asymmetry inside their hidden layers, and we test it causally: given two images, we transplant the phase of one onto the magnitude of the other at a chosen layer and record which image the prediction follows. In PRISM2D, GFNet, and ViT-B/16 the prediction follows the phase or sign donor, and deleting all image-specific magnitude barely moves accuracy, so identity rides on phase while image-specific magnitude is largely dispensable to the readout. ResNet-50 at first seems to break the pattern, because transplanting sign after its ReLUs does nothing; a fair intervention before the ReLU reveals a strong latent sign code in the late blocks, and a DC-only control shows the readout consumes a channel-wise spatial average. Controls rule out the trivial case in which magnitude simply stops depending on the image. The architectures therefore share a phase/sign identity code but expose it in different bases, set by rectification and readout geometry, which gives a mechanistic account of the texture--shape gap between CNNs and attention models.

Alper Yıldırım

Visual Representation Learning Frequency-Domain Feature Learning Image Classification

Jun 15, 2026cs.CV

Hierarchical Fine-Grained Aerial Object Detection

Fine-grained aerial object detection, driven by the intrinsic granularity of real-world object categories, is crucial for advanced scene understanding in remote sensing. Existing methods largely inherit the paradigm of coarse-grained object detection, relying solely on single-label supervision and thus struggling to distinguish model-level categories with subtle structural differences. However, for each specific model (e.g., Boeing 787), structured prior knowledge such as attributes and hierarchies offers discriminative semantics across multiple granularities. Motivated by this, we present ExpertDet, a scheme that incorporates expert-informed cues to enhance fine-grained aerial object detection. Specifically, we design Vision-aware Masked Attribute Modeling (VMAM), which aligns attribute semantics with visual structures by reconstructing randomly masked attributes from visual cues, enabling the detector to capture subtle structural distinctions. We further propose Hierarchical Visual Instance Promotion (HierVIP), which builds a visual prototype tree based on hierarchical relations and imposes taxonomy-aware constraints to preserve cross-level semantic continuity while enhancing category discrimination. Moreover, we curate a new fine-grained object detection benchmark for Precise recognition of model-specific Ships and Planes from aerial imagery, PSP, covering 106 ship classes and 30 airplane models, respectively, featuring the most extensive collection of model-specific categories among existing aerial object detection datasets to date. We benchmark state-of-the-art object detection algorithms on the PSP benchmark. Extensive evaluation demonstrates that ExpertDet consistently outperforms other fine-grained competitors across hierarchy levels. The dataset, benchmark, and code are available at https://nnnnerd.github.io/PSP-Benchmark/.

Yan Zhang, Fang Xu, Wen Yang +1

School of Computer Science, Wuhan University, Wuhan, 430072, China · School of Artificial Intelligence, Wuhan University, Wuhan, 430072, China · School of Electronic Information, Wuhan University, Wuhan, 430072, China

Visual Representation Learning Hierarchical Representation Learning Remote Sensing Benchmarks Aerial Object Detection

Jun 14, 2026cs.CV

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

Progress in AI has largely been driven by methods that assume less. As compute and data increase, approaches with weaker inductive biases generally outperform those with stronger assumptions. This is particularly characteristic of the field of Visual Representation Learning, where approaches have gone from being dominated by Supervised Learning, to Weakly Supervised Learning, to the now widespread success of Self-Supervised Learning without human labels. Yet, even modern Self-Supervised Learning approaches still depend on strong inductive biases such as augmentations, masking, or cropping. If this trend holds, even these remaining biases should become bottlenecks at scale -- and our experiments confirm this: the optimal strength of inductive biases decreases as data grows. This motivates the search for approaches that rely on fewer assumptions. To this end, we introduce Temporal Difference in Vision (TDV), a new paradigm for self-supervised learning from video that avoids existing inductive biases, relying instead on a causal assumption that the past causes the future. TDV functions by jointly training an image encoder and a motion encoder so that the current frame's representation plus the encoded motion equals the next frame's representation. Despite not leveraging any strong inductive biases, TDV matches state-of-the-art recipes on dense spatial tasks, laying the foundation for representation learning without strong assumptions.

Ninad Daithankar, Alexi Gladstone, Yann LeCun +1

1UIUC · 2New York University

Visual Representation Learning Video Representation Learning Self-Supervised Visual Representation Learning

Jun 13, 2026cs.CV

Analyzing Visual Aircraft Representations with Sparse Autoencoders

Vision models can achieve strong performance on classification tasks, but the internal representations supporting their predictions are often difficult to interpret. This work investigates whether sparse autoencoders can decompose intermediate representations of a vision model into interpretable features. We train a ConvNeXt classifier on the FGVC-Aircraft dataset, extract spatial activations from its final feature stage, and train a sparse autoencoder on these activations. The learned sparse features are analyzed using top-activating image patches, activation strength, and class selectivity. Qualitative visual inspection reveals that several features correspond to recognizable aircraft structures and visual patterns. We evaluate a subset of selected features using input-space and feature-space ablations, measuring how blurring image patches and suppressing sparse features affect class logits, classification margins, and prediction confidence. The results suggest that sparse autoencoders can reveal partially interpretable, class-relevant visual features associated with aircraft recognition, while also exposing limitations such as polysemanticity and coarse spatial localization.

Deepshik Sharma

Department of Computer Science & Engineering · Jain University, Bangalore, India

Visual Representation Learning Sparse Autoencoders Neural Network Interpretability

Jun 13, 2026cs.RO

Rethinking Implicit Spatial Representation in Visuomotor Policy Learning

Generative model-based imitation learning has become a widely adopted paradigm for robotic manipulation, where policy performance depends critically on the conditioned visual representations. Although spatial softmax-based representations have been adopted in prior visuomotor policies, their effectiveness and underlying mechanisms remain insufficiently understood. This work rethinks the use of spatial softmax pooling: do such implicit spatial representations provide effective and stable visual features for robotic manipulation? Through systematic studies of different pooling methods in visual encoders, we find that this pooling operation produces compact and stable spatial representations, which outperform feature-value representations, despite using substantially fewer dimensions. Complementary saliency analysis further suggests that these spatial representations guide the encoder to focus more consistently on task-relevant regions. However, this advantage is limited by a representation bottleneck in current visual encoders: repeated downsampling operations weaken fine-grained spatial information before the action-generation module can use it, especially under low-resolution observations. Motivated by these findings, we propose PRISM, a visual encoder that preserves multiscale implicit spatial information through top-down cross-attention fusion. Experiments across multiple tasks and policy backbones show consistent improvements. In particular, on the low-resolution, high-precision ToolHang task, PRISM shows clear gains, improving the average success rate from 5.0% to 13.4% while increasing parameters by only 15.4%. These results support the use of multiscale implicit spatial representations as an effective and efficient design principle for robotic manipulation.

Xiangyu Chen, Yuxuan Hu, Chuhao Zhou +1

MARS Lab, Nanyang Technological University

Visual Representation Learning Visuomotor Policy Learning Multi-Scale Feature Fusion Robotic Manipulation Robot Imitation Learning

Jun 13, 2026cs.CV

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched. A multimodal large language model (MLLM), shown the same pair, can articulate those attributes and use them to predict whether the images share a class. We propose \textbf{SAGA}, a framework that turns this language-grounded, attribute-aware perception into a training signal for the encoder itself. Specifically, we use Group Relative Policy Optimization (GRPO) to reward the MLLM for correct predictions on the vision encoder's tokens. Since correct predictions require those tokens to expose the specific attributes that differ or match between the pair, the gradient pushes the encoder to encode them, replacing the uniform pair-level scalar with attribute-resolved supervision. An auxiliary attention-distillation loss anchors the encoder's embedding to tokens the MLLM attended to, and a standard metric-learning loss shapes the embedding geometry for nearest-neighbour retrieval. The MLLM is frozen throughout and discarded at inference, matching the deployment cost of a metric-learning baseline. SAGA improves Recall@1 by 3 to 6 points over state-of-the-art baselines on CUB-200-2011, Cars-196, FGVC-Aircraft, and iNaturalist Aves on zero-shot image retrieval.

Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja

University of Illinois Urbana-Champaign

Visual Representation Learning Fine-Grained Image Retrieval Metric Learning Vision-Language Retrieval

Jun 12, 2026cs.LG

Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders

Scientific user facilities generate X-ray scattering data faster than traditional workflows can process them. We address this challenge across two settings, offline dataset exploration and live on-the-fly analysis. We train a domain-specific attention-based Convolutional Variational Autoencoder (C-VAE) on 1.5 million X-ray scattering images to learn low-dimensional representations capturing structural variation across diverse experimental conditions. The learned latent space reveals well-organized clusters and smooth trajectories reflecting experimental progression. It further supports controlled synthetic scattering image generation across diverse structural states. When deployed without retraining, the model organizes time-resolved film formation experiments at two synchrotron facilities into interpretable latent structures. Benchmarking against DINOv3 (ViT-7B), a general-purpose vision foundation model, demonstrates that domain-specific training yields more interpretable latent organization for scattering data. Both workflows are integrated within Latent Space Explorer, a component of the MLExchange platform, supporting interactive structural exploration across archived datasets and live experiments.

Monika Choudhary, Xiaoya Chong, Runbo Jiang +25

Variational Autoencoders Visual Representation Learning

Jun 12, 2026cs.CV

RATS! Patches Talk Through Registers: Emergent Parts in Register Attention Transformers

When humans see a bird, they recognize far more than just "bird" -- they see a head, wings, and talons, a structured assembly of reusable parts that can be identified across every bird they have ever seen. We ask whether a self-supervised visual model can discover the same compositional structure on its own. To this end, we propose RATS (Register Attention Transformers), which decomposes the classification token into N learnable register tokens that route patch information through an L->N->N->L bottleneck via a three-step compress-communicate-broadcast attention. The N registers are partitioned across the H attention heads, so that registers assigned to different heads do not interact with each other. Without auxiliary losses or part annotations, each register spontaneously specializes into a proto-semantic region whose emerging structure resembles object parts. RATS surpasses all baselines by +12 mIoU on average across five segmentation benchmarks, with consistent gains on ADE20K (+1.11 mIoU) and COCO (+0.2 AP^m). Its register dictionary further exhibits part-level consistency and semantic proximity across related categories. Our results suggest that RATS may provide a useful architectural prior for structured and interpretable visual representation learning.

Timing Yang, Predrag Neskovic, Jansen Seheult +4

1Johns Hopkins University · 2Office of Naval Research, Arlington, VA · Department of Laboratory Medicine and Pathology, Mayo Clinic,FLOPs (G)MN, USA

Visual Attention Visual Representation Learning Vision Transformer Object-Centric Representation Learning Compositional Representation Learning Semantic Segmentation+1

Jun 9, 2026cs.CV

IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder

Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing semantically rich latent spaces for image generation. However, their reconstruction quality often remains suboptimal, largely because deep VFM representations do not preserve sufficient fine-grained visual detail. This limitation becomes even more severe after discretization, where missing low-level information is difficult to recover. In fact, we observe that shallow VFM features retain considerably richer local appearance and structural detail, which complements the high-level semantics carried by deep features used in existing RAEs. Motivated by this complementary property, we propose Ideal, an In-depth Alignment framework for discrete representation autoencoding. By jointly aligning quantized tokens with both shallow and deep VFM features, Ideal enables the resulting discrete visual tokens to preserve both visual fidelity and rich semantics. Extensive experiments demonstrate that Ideal yields superior reconstruction performance, achieving 0.61 rFID on ImageNet and outperforming the previous best method by 0.28. When used for autoregressive image generation, Ideal further produces a gFID of 1.89, establishing a new state of the art for autoregressive image generation.

Yitong Chen, Zijie Diao, Junke Wang +5

Institute of Trustworthy Embodied AI, Fudan University · Shanghai Innovation Institute · University of Maryland, College Park

Visual Representation Learning Image Tokenization Autoencoders Image Reconstruction Autoregressive Image Generation Visual Token Compression

Jun 5, 2026cs.CV

Lighting-Aware Representation Learning under Controllable Lighting Variation

Variations in illumination remain a major challenge for visual representation learning, as they induce substantial appearance changes both across and within environments. While existing approaches typically address this issue through data augmentations that encourage models to become invariant to lighting changes, such strategies do not explicitly model lighting information during learning. Inspired by theories of human vision, we propose a lighting-aware representation learning framework that incorporates illumination variation as an explicit training signal rather than a nuisance factor to be suppressed. Our method extends contrastive learning by introducing an auxiliary objective that captures illumination-dependent variation in rendered scenes, enabling the model to jointly learn representations that preserve semantic consistency while remaining sensitive to lighting-dependent visual structure. We evaluate the proposed model on image classification and object detection tasks across the ImageNet, ExDark, and PASCAL VOC benchmarks. Results demonstrate that the proposed lighting-aware training consistently improves downstream performance over standard contrastive learning baselines, while maintaining the same architecture and training budget. Furthermore, our approach shows promising performance in supervised learning frameworks and under settings involving simpler lighting variation, suggesting broad applicability beyond complex illumination scenarios. These results indicate its potential to enhance model robustness and adaptability in complex visual environments as well as in more conventional image processing tasks.

Lizhen Zhu, Charantej Reddy Pochimireddy, James Z Wang +1

Department of Informatics and Intelligent Systems, College of Information Sciences and Technology, The Pennsylvania State University, University Park, PA, 16802, USA · Department of Psychology, College of the Liberal Arts, The Pennsylvania State University, University Park, PA, 16802, USA

Contrastive Learning Visual Representation Learning Distribution Shift

Jun 3, 2026cs.CV

Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning

Learning semantics is essential for deep learning models to be interpretable and better aligned with human reasoning. Concept-based models approach this by representing classes through meaningful semantic abstractions, but typically treat all concepts as a flat, unstructured set learned at a single neural network layer. This overlooks a fundamental property of human semantic understanding: concepts being organized hierarchically, from general to specific. While deep networks do learn a hierarchy of visual features, this structure is rarely aligned with explicit semantic hierarchies. Drawing on Formal Concept Analysis, we demonstrate that formal concept lattices provide principled semantic scaffolds to guide neural network learning. These lattices naturally identify where in the network concepts should be learned based on their level of generality. This allows the model to develop staged, semantically grounded representations throughout its depth. Empirical results on real-world datasets show that our models produce more interpretable embeddings, support more effective interventions, and learn concept representations that are both meaningful and hierarchically structured.

Deepika SN Vemuri, Sayanta Adhikari, Ankit Saha +2

IIT Hyderabad · Amazon, India · KLA +1

Visual Representation Learning Interpretable ML Hierarchical Representation Learning Formal Concept Analysis

Jun 3, 2026cs.CV

Stateful Visual Encoders for Vision-Language Models

Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, visual comparisons happen only inside the language model, while the visual encoder itself remains stateless: each image is encoded independently, without access to the prior visual context. As a result, small but task-critical changes may be attenuated before the language model has a chance to compare them, especially when those changes do not affect the high-level semantics of the scene. We introduce a Stateful Visual Encoder, which conditions each visual representation on prior visual features. Under supervised finetuning, VLMs equipped with stateful encoders achieve consistent improvements on controlled tasks involving cross-image spatial aggregation, multi-object visual differencing, and visual trajectory behavior cloning. These improvements are consistent across input resolutions, language model sizes, and VLM backbones. Finally, we validate our model on real-world tasks, including longitudinal radiology, fine-grained image comparison, and remote sensing, where stateful encoders consistently improve generalist VLM baselines and can match or surpass specialized models in selected domains. Project page: https://statefulvisualencoders.github.io/

Zirui Wang, Junwei Yu, Adam Yala +3

1Voio, Inc. · 2UC Berkeley · 3UCSF

Vision-Language Models Visual Representation Learning VLM Adaptation

Jun 2, 2026cs.CV

Formalizing the Binding Problem

Representations of the world, arguably, contain information about features (e.g. something is blue, something is a circle) but also information about which features are part of the same object (e.g. the circle is blue), which we call binding information. Any system with the ability to understand scenes with multiple objects must be able to solve the binding problem: it needs to know which features belong together. However, despite work showing that Vision Transformers (ViTs) know which patches belong together, it is not known whether current deep learning models learn to exhibit binding information, i.e., for features. We may believe that there is not much binding information, after all misattributing features to wrong objects is a common failure of ViT-based architectures, especially in scenes with objects sharing features. Here we formalize the binding problem with an information-theoretic approach, and introduce a probing method to measure binding information in model representations. We perform experiments on ViTs, measuring binding from different components of the architecture, such as the image summary token [CLS] or the spatial tokens. We use datasets with different binding challenges, such as feature sharing, occlusion, and natural features, while comparing the performance of several pre-trained ViTs. Overall, our research demonstrates binding as a key ingredient to strong visual recognition and reasoning.

Lianghuan Huang, Yihao Li, Saeed Salehi +3

Department of Physics and Astronomy, University of Pennsylvania, Philadelphia, PA, USA · Department of Computer and Information Science, University of Pennsylvania · Machine Learning Group, Technical University of Berlin, Berlin, Germany +3

Visual Representation Learning Vision Transformer

Jun 2, 2026cs.CV

Beyond Compression: Quantifying Spectral Accessibility in Vision Representations

Vision-language models map visual features into a shared embedding space through learned projection layers, yet it remains unclear how these transformations alter the structure of visual information. This study examines changes in representation through spatial-frequency accessibility, measured by the linear recoverability of band-limited Fourier energy from model representations. To isolate effects beyond dimensionality reduction, we introduce Residual Spectral Loss (RSL), which evaluates changes relative to a dimension-matched random projection baseline. To reduce confounding effects from optimization, the analysis uses pretrained models with all parameters frozen. The experimental results show consistent frequency-dependent changes in accessibility across CLIP and DINOv2 on ImageNet and MS-COCO datasets. Spectral accessibility follows a non-monotonic trajectory across depth, peaking at intermediate layers before decreasing toward the output representation. The final transformation differs across architectures: CLIP's learned projection is spectrally neutral, with changes explained by compression, whereas DINOv2's [CLS] pooling induces a structured loss across the spectrum. These findings identify intermediate layers and pooling mechanisms as primary drivers of spectral transformation in modern vision encoders.

Akayou A. Kitessa, Yijun Zhao

Fordham University New York City, NY

Visual Representation Learning Frequency-Domain Feature Learning VLM Interpretability

May 29, 2026cs.CV

PRISM: Progressive Reasoning through Iterative Slot Memory for Vision

Modern vision models process images in a single feed-forward pass, which limits their ability to recover missing evidence or refine uncertain representations under incomplete observations. Inspired by the iterative nature of human perception, we introduce PRISM (Progressive Reasoning through Iterative Slot Memory), a pyramid vision architecture that reasons over images through iterative refinement. At a high level, PRISM groups visual features into object-centric representations, retrieves relevant patterns from a learned memory, and iteratively refines the representation to resolve ambiguity and recover missing information. This organize-recall-refine process operates recurrently across multiple scales, enabling progressive improvement of visual representations. Across standard vision tasks, including image classification, object detection, and semantic segmentation, PRISM achieves competitive performance while demonstrating improved robustness under incomplete observations such as occlusion. These results suggest that iterative reasoning with structured representations and memory is a promising direction for building more resilient and adaptive vision models. Source code and models will be released.

Ziyu Wang, Shuangpeng Han, Mengmi Zhang

Deep NeuroCognition Lab, Nanyang Technological University, Singapore

Visual Representation Learning Visual Reasoning