Visual Representation Learning

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

245 papers26 papers in the last four weeks, down 24% on the four weeks before. 0.2% of all new papers.

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

    Sep 19, 2025An Dinh Vuong, Minh Nhat Vu, Ian ReidVisual Representation LearningVisuomotor Policy Learning

  2. Disentangling Latent Embeddings with Sparse Linear Concept Cones (SLiCC)

    Aug 27, 2025Zhi Li, Hau Phan, Matthew Emigh +1Sparse CodingDisentangled Representation Learning

  3. GViT: Representing Images as Gaussians for Visual Recognition

    Jun 30, 2025Jefferson Hernandez, Ruozhen He, Guha Balakrishnan +2Image ClassificationVisual Representation Learning

  4. Employing Discrete Fourier Transform in Representation Learning

    Jun 7, 2025Raoof HojatJalali, Edmondo TrentinVisual Representation LearningFrequency-Domain Feature Learning

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

    Feb 20, 2025Yuling Jiao, Wensen Ma, Defeng Sun +2Visual Representation LearningDistribution Matching