Visual Representation Learning

Ask about this topic

Overview

Visual representation learning studies how to turn images and video into features that preserve information useful for tasks such as classification, segmentation, retrieval, and robotic control. Common approaches include contrastive and masked-image learning, predictive methods such as joint-embedding models, generative objectives, and supervision from language, geometry, or action. Vision foundation models are increasingly evaluated beyond ImageNet classification, on dense prediction, robustness to visual shifts, compositional reasoning, and real-world manipulation. A central tension is how to make features broadly transferable and efficient while retaining fine spatial detail, task-relevant information, and reliability under distribution changes.

Latest papers

CardsList

224 papers26 papers in the last four weeks, down 7% on the four weeks before. 0.2% of all new papers.

Feb 16, 2026

MeFEm: Medical Face Embedding model

We present MeFEm, a vision model based on a modified Joint Embedding Predictive Architecture (JEPA) for biometric and medical analysis from facial images. Key modifications include an axial stripe masking strategy to focus learning on semantically relevant regions, a circular loss weighting scheme, and the probabilistic reassignment of the CLS token for high quality linear probing. Trained on a consolidated dataset of curated images, MeFEm outperforms strong baselines like FaRL and Franca on core anthropometric tasks despite using significantly less data. It also shows promising results on Body Mass Index (BMI) estimation, evaluated on a novel, consolidated closed-source dataset that addresses the domain bias prevalent in existing data. Model weights are available at https://huggingface.co/boretsyury/MeFEm , offering a strong baseline for future work in this domain.

Yury Borets, Stepan Botman

Sber AI Lab

Visual Representation LearningJoint-Embedding Predictive Architecture
AskPDF
Feb 5, 2026

Semantic Purification for Conditional Representation Learning

Conditional representation learning aims to extract criterion-specific features for customized tasks. Recent methods construct conditional subspaces spanned by criterion-specific text bases in the embedding space of vision-language models (VLMs). Image embeddings are then projected onto these subspaces to obtain conditional representations. However, since VLMs are not explicitly trained to disentangle semantics associated with different criteria, the corresponding conditional subspaces remain coupled. This coupling induces semantic leakage during projection, thereby degrading the semantic purity of conditional representations. To suppress semantic leakage, we propose Semantic Purification for Conditional Representation Learning (SP-CRL). Specifically, SP-CRL first decomposes the original text basis and performs curvature-based adaptive truncation on the resulting basis vectors to construct a purer conditional subspace. It then identifies an appropriate noise subspace and projects image embeddings onto its null space to remove irrelevant semantic components. Extensive experiments across customized clustering, customized few-shot classification, and customized retrieval tasks demonstrate that SP-CRL achieves state-of-the-art performance with superior generalization.

Jiaquan Wang, Yan Lyu, Chen Li +1

School of Computer Science and Engineering, Southeast University, China · Biomedicine Discovery Institute, Department of Biochemistry and Molecular Biology, Monash University, Australia

Disentangled Representation LearningRepresentation LearningCross-Modal Representation LearningVisual Representation Learning
AskPDF
Jan 29, 2026

Spotlighting Task-Relevant Features: Object-Centric Representations for Better Generalization in Robotic Manipulation

The generalization capabilities of robotic manipulation policies are heavily influenced by the choice of visual representations. Existing approaches typically rely on representations extracted from pre-trained encoders, using two dominant types of features: global features, which summarize an entire image via a single pooled vector, and dense features, which preserve a patch-wise embedding from the final encoder layer. While widely used, both feature types mix task-relevant and irrelevant information, leading to poor generalization under distribution shifts, such as changes in lighting, textures, or the presence of distractors. In this work, we explore an intermediate structured alternative: Slot-Based Object-Centric Representations (SBOCR), which group dense features into a finite set of object-like entities. This representation permits to naturally reduce the noise provided to the robotic manipulation policy while keeping enough information to efficiently perform the task. We benchmark a range of global and dense representations against intermediate slot-based representations, across a suite of simulated and real-world manipulation tasks ranging from simple to complex. We evaluate their generalization under diverse visual conditions, including changes in lighting, texture, and the presence of distractors. Our findings reveal that SBOCR-based policies outperform dense and global representation-based policies in generalization settings, even without task-specific pretraining. These insights suggest that SBOCR is a promising direction for designing visual systems that generalize effectively in dynamic, real-world robotic environments.

Alexandre Chapin, Bruno Machado, Emmanuel Dellandréa +1

LIRIS, imagine

Visual Representation LearningGeneralization in Robotic ManipulationObject-Centric Representation LearningRobotic ManipulationRobot Policy Generalization
AskPDF
Jan 20, 2026

MTV: Revisiting Multi-Task Visual Representation Learning

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.

Shangzhe Di, Zhonghua Zhai, Weidi Xie

SAI, Shanghai Jiao Tong University · ByteDance Seed

Visual Representation LearningSelf-Supervised Visual Representation LearningVision-Language Pretraining
AskPDF
Jan 14, 2026

Geometric Stability: The Missing Axis of Representations

Representational similarity methods compare the geometries of neural representations, but they do not measure how consistently the geometry of a single representation is recovered from subsets of its feature coordinates. We call this property geometric stability and introduce Shesha, which estimates it by correlating representational dissimilarity matrices from complementary random feature subsets. Shesha is not invariant to orthogonal rotations: representations with identical Gram matrices, and therefore identical linear CKA, can have different geometric stability. Controlled transformations further separate the quantities. Across 2,4632{,}463 encoder configurations spanning seven domains, similarity and stability are positively associated across non-PCA transformations (ρ=+0.75ρ=+0.75) but negatively associated under PCA-coordinate compression (ρ=−0.47ρ=-0.47). We further evaluate 170 pretrained vision models across six datasets. DINOv2 combines strong transfer performance with bottom-quartile stability on five of six datasets, showing that transferability and feature-split stability need not coincide. Across random feature subsets, the marginal relationship between Shesha and linear-probe variability is dataset-dependent; after controlling for task alignment with LogME, higher Shesha is associated with lower variability on five of six datasets. These results identify geometric stability as a basis-dependent property that complements representational similarity and task alignment.

Prashant C. Raju

Representational Similarity AnalysisNeural Representation GeometryVisual Representation LearningGeometric Representation Learning
AskPDF
Jan 11, 2026

Enhancing Low-resolution Image Representation Through Normalizing Flows

Low-resolution image representation can be regarded as a special form of sparse representation that retains only low-frequency information while discarding high-frequency components. This property reduces storage and transmission costs and benefits various image processing tasks. However, a key challenge is to preserve essential visual content while maintaining the ability to accurately reconstruct the original images. This work proposes LR2Flow, a nonlinear framework that learns low-resolution image representations by integrating wavelet tight frame blocks with normalizing flows. We conduct a reconstruction error analysis of the proposed network, which demonstrates the necessity of designing invertible neural networks in the wavelet tight frame domain. Experimental results on various tasks, including image rescaling, compression, and denoising, demonstrate the effectiveness of the learned representations and the robustness of the proposed framework. Code is available at https://github.com/Evanescentlove/LR2Flow-main.

Chenglong Bao, Tongyao Pang, Zuowei Shen +2

Yau Mathematical Sciences Center, Tsinghua University, Beijing, China, and Beijing Institute of Mathematical Sciences and Applications, Beijing, China · Yau Mathematical Sciences Center, Tsinghua University, Beijing, China · Department of Mathematics, National University of Singapore, Singapore +2

Learned Image CompressionNormalizing FlowsVisual Representation Learning
AskPDF
Dec 9, 2025

Is Generation Required for Data-Efficient Perception?

It has been hypothesized that achieving the data efficiency of human visual perception requires a generative approach in which internal representations result from inverting a decoder. Yet today's most successful vision models are non-generative, relying on an encoder that maps images to representations without decoder inversion. This raises the question of whether generation is necessary for data-efficient machine perception. To address this, we study to what extent generative and non-generative methods can achieve compositional generalization, a hallmark of human data efficiency. Under a compositional generative process, we formally characterize the inductive biases required for compositional generalization in decoder-based (generative) and encoder-based (non-generative) methods. We show theoretically that the inductive biases required for an encoder are substantially more complex and generally infeasible to impose explicitly through architectural constraints or regularization. By contrast, the decoder biases take a simple form that can be enforced directly. These results suggest that compositional generalization may be substantially easier to achieve through a generative paradigm of learning and inverting a decoder rather than learning an encoder directly. We examine our theoretical findings empirically by training a range of generative and non-generative methods on synthetic image data. We find that non-generative methods often fail to generalize compositionally and require large-scale pretraining to improve generalization. By comparison, generative methods yield gains in generalization without requiring additional data.

Jack Brady, Bernhard Schölkopf, Thomas Kipf +2

Max Planck Institute for Intelligent Systems, Tübingen, Germany · Tübingen AI Center · ELLIS Institute, Tübingen +1

Visual Representation LearningGenerative ModelingInductive BiasCompositional GeneralizationData-Efficient Learning
AskPDF
Nov 14, 2025

Φeat: Physically Grounded Material Feature Representation

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 ΦΦeat$, 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.

Giuseppe Vecchio, Adrien Kaiser, Claudia Cuttano +4

Adobe Research, France

Representation LearningVisual Representation LearningSelf-Supervised Visual Representation Learning
AskPDF
Sep 30, 2025

SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition

Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the dynamic interplay between spatial context and visual similarity during training. We present SAGE (Spatial-visual Adaptive Graph Exploration), a unified training pipeline that enhances granular spatial-visual discrimination by jointly improving local feature aggregation, organize samples during training, and hard sample mining. We introduce a lightweight Soft Probing module that learns residual weights from training data for patch descriptors before bilinear aggregation, boosting distinctive local cues. During training we reconstruct an online geo-visual graph that fuses geographic proximity and current visual similarity so that candidate neighborhoods reflect the evolving embedding landscape. To concentrate learning on the most informative place neighborhoods, we seed clusters from high-affinity anchors and iteratively expand them with a greedy weighted clique expansion sampler. Implemented with a frozen DINOv2 backbone and parameter-efficient fine-tuning, SAGE achieves SOTA across eight benchmarks. Notably, our method obtains 100% Recall@10 on SPED only using 4096D global descriptors. The code and model are available at https://github.com/chenshunpeng/SAGE.

Shunpeng Chen, Changwei Wang, Rongtao Xu +7

School of Artificial Intelligence, Beijing University of Posts and Telecommunications · Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology · Spatialtemporal AI

Visual Representation LearningGeospatial Representation LearningVisual Place Recognition
AskPDF
Sep 29, 2025

SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation

Pre-trained diffusion models provide rich latent features across U-Net levels and are emerging as powerful vision backbones. While prior works such as Marigold and Lotus repurpose diffusion priors for dense geometric perception tasks such as depth and surface normal estimation, their potential for cross-domain human pose estimation remains largely unexplored. Through a systematic analysis of latent features from different upsampling levels of the Stable Diffusion U-Net, we identify the levels that deliver the strongest robustness and cross-domain generalization for pose estimation. Building on these findings, we propose SDPose, which (i) extracts U-Net features from the selected upsampling blocks, (ii) fuses them with a lightweight feature aggregation module to form a robust representation, and (iii) jointly optimizes keypoint heatmap supervision with an auxiliary latent reconstruction loss to regularize training and preserve the pre-trained generative prior. To evaluate cross-domain generalization and robustness, we construct COCO-OOD, a COCO-based benchmark with four subsets: three style-transferred splits to assess domain shift and one corruption split (noise, weather, digital artifacts, and blur) to test robustness. With data-efficient fine-tuning, SDPose achieves performance comparable to Sapiens on COCO, and establishes the best zero-shot performance on cross-domain datasets.

Shuang Liang, Jing He, Lejun Liao +4

Rama Alpaca Technology · The University of Hong Kong · HKUST (GZ) +3

Human Pose EstimationVisual Representation Learning
AskPDF
Sep 29, 2025

Improved Robustness from Biologically Inspired Sparse Contrast Representations

Deep neural networks surpass humans on many vision benchmarks, yet remain far less robust to distribution shifts such as illumination and weather changes. Existing approaches address this challenge by additional training data, extensive augmentation, architectural modifications, or test-time adaptation. In this work, we explore a complementary direction: inspired by the human retina, we propose a fixed, model-agnostic preprocessing module that extracts signals that are more stable with respect to variations of illumination. Our method combines color remapping with local contrast extraction, producing sparse representations that emphasize structural features. We study its impact on semantic segmentation by training on Cityscapes and evaluating generalization under adverse conditions on Dark Zurich and ACDC. Our results show that the biologically inspired preprocessing preserves in-distribution performance while consistently improving robustness in challenging lighting scenarios, such as nighttime, where annotated training data are scarce. Moreover, the segmentation accuracy remains stable even when the contrast-based representation is sparsified by up to 70%. These gains suggest that rethinking the input representation itself can improve robustness while also opening opportunities for lower-latency, transmission-aware imaging sensors when sparsity can be exploited close to acquisition.

Lorena Stracke, Lia Nimmermann, Shashank Agnihotri +3

Media Systems, University of Siegen, Germany · Data and Web Science Group, University of Mannheim, Germany · Analogue Circuits and Image Sensors, University of Siegen, Germany +1

Distribution Shift RobustnessImage SegmentationImage Corruption RobustnessVisual Representation LearningNeural Network RobustnessSemantic Segmentation
AskPDF
Sep 19, 2025

eVGGT: An Efficient Geometry-Aware Vision Encoder for Visuomotor Policies

Geometry-grounded vision models, such as VGGT, have emerged as robust visual encoders, providing essential geometric priors for robotic manipulation. However, the high computational cost of these models often leads to slow inference, limiting their practical applications in real-world robotics. This paper introduces eVGGT, a lightweight geometry-aware vision encoder distilled from the high-performing VGGT. Our findings demonstrate two primary advantages: i) integrating eVGGT into imitation learning frameworks (including ACT and Diffusion Policy) yields up to a 6.3% improvement in success rate over standard 2D encoders across bimanual and single-arm tasks in both simulation and real-world settings with variable viewpoints; ii) eVGGT achieves a nearly 5 times speedup and a 63% reduction in memory usage compared to state-of-the-art geometry-aware encoders while maintaining comparable task performance. These results suggest that eVGGT substantially alleviates the performance-latency bottleneck that has limited geometry-aware visuomotor policies in real-world deployment.

An Dinh Vuong, Minh Nhat Vu, Ian Reid

Department of Computer Vision, Mohammed bin Zayed University of Artificial Intelligence, UAE · AIT Austrian Institute of Technology GmbH, Austria

Visual Representation LearningVisuomotor Policy LearningGeometric Representation LearningRobotic Manipulation
AskPDF
Jun 7, 2025

Employing Discrete Fourier Transform in Representation Learning

Image representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach uses autoencoders to extract latent representations at the network's compression point. These representations are valuable because they retain essential information necessary for reconstructing the original input from the compressed latent space. In this paper, we propose an alternative learning objective. Instead of using the raw input as the reconstruction target, we employ the Discrete Fourier Transform (DFT) of the input. The DFT provides meaningful global information at each frequency level, making individual frequency components useful as separate learning targets. When dealing with multidimensional input data, the DFT offers remarkable flexibility by enabling selective transformation across specific dimensions while preserving others in the computation. Moreover, certain types of input exhibit distinct patterns in their frequency distributions, where specific frequency components consistently contain most of the magnitude, allowing us to focus on a subset of frequencies rather than the entire spectrum. These characteristics position the DFT as a viable learning objective for representation learning. We validate our approach on the CIFAR-10 and STL-10 datasets under constrained training regimes. We discovered that integrating data augmentation during pretraining enhances the learned representations. Furthermore, we demonstrate that training exclusively on the lower-frequency components, those containing the highest magnitudes, produces results comparable to using the full frequency spectrum with only minimal reductions in accuracy.

Raoof HojatJalali, Edmondo Trentin

Universit‘a di Siena, Italy · DIISM, Universit‘a di Siena, Italy

Visual Representation LearningFrequency-Domain Feature Learning
AskPDF
Feb 20, 2025

Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching

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 push-forward law matches an explicit reference law. The reference law specifies what the learned representation distribution should look like, while the matching mechanism determines how this target is matched. Within DM, generative learning and representation learning can be viewed as directionally inverse distributional processes: generative learning maps a tractable reference to data, whereas representation learning maps data to a designed reference law. For the Mallows-distance instantiation studied here, we connect the population objective to class-centre separation and classification error and derive a finite-sample bound on downstream classification error. Simulations and image benchmarks show manifold rectification, fine-grained structure and transferability.

Yuling Jiao, Wensen Ma, Defeng Sun +2

School of Artificial Intelligence, Wuhan University, 430072, Wuhan, China · School of Mathematics and Statistics, Wuhan University, Wuhan, 430072, China · Department of Applied Mathematics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China +2

Visual Representation LearningDistribution MatchingTransfer LearningInvariant Representation LearningSelf-Supervised Visual Representation Learning
AskPDF