Self-Supervised Visual Representation Learning

Overview

The field studies how visual models can learn useful features without relying on large collections of human-labeled images or videos, enabling transfer to tasks such as classification, segmentation, recognition, and robotic control. Common approaches include contrastive learning across augmented views, masked autoencoders that reconstruct hidden content, self-distillation, and joint-embedding predictive architectures that predict latent features; video and multi-view methods also use temporal and geometric consistency. These methods are evaluated on benchmarks such as ImageNet and COCO, as well as video, 3D, and specialized medical or remote-sensing tasks, with large pretrained encoders often adapted using lightweight probes or fine-tuning. A central tension is how to learn features that are both broadly transferable and sensitive to spatial detail, motion, geometry, or domain-specific cues, while avoiding shortcuts and representation collapse.

Latest papers

CardsList

257 papers27 papers in the last four weeks, down 34% on the four weeks before. 0.2% of all new papers.

  1. US-JEPA: A Joint Embedding Predictive Architecture for Ultrasound

    Feb 22, 2026Ashwath Radhachandran, Vedrana Ivezić, Shreeram Athreya +2Joint-Embedding Predictive ArchitectureUltrasound Imaging

  2. Human-level 3D shape perception emerges from multi-view learning

    Feb 19, 2026Tyler Bonnen, Jitendra Malik, Angjoo KanazawaMulti-View LearningSelf-Supervised Visual Representation Learning

  3. A Self-Supervised Approach for Enhanced Feature Representations in Object Detection Tasks

    Feb 18, 2026Santiago C. Vilabella, Pablo Pérez-Núñez, Beatriz RemeseiroObject DetectionSelf-Supervised Visual Representation Learning

  4. Benchmarking Self-Supervised Models for Cardiac Ultrasound View Classification

    Feb 17, 2026Youssef Megahed, Salma I. Megahed, Robin Ducharme +4Self-Supervised Visual Representation LearningEchocardiography

  5. Hypersolid: Emergent Vision Representations via Short-Range Repulsion

    Jan 29, 2026Esteban Rodríguez-Betancourt, Edgar Casasola-MurilloUnsupervised LearningRepresentation Learning

  6. DeFM: Learning Foundation Representations from Depth for Robotics

    Jan 26, 2026Manthan Patel, Jonas Frey, Mayank Mittal +5Representation LearningRobot Foundation Models

  7. MTV: Revisiting Multi-Task Visual Representation Learning

    Jan 20, 2026Shangzhe Di, Zhonghua Zhai, Weidi XieVisual Representation LearningSelf-Supervised Visual Representation Learning

  8. KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning

    Dec 22, 2025Eric Zimmermann, Harley Wiltzer, Justin Szeto +2Joint-Embedding Predictive ArchitectureSelf-Supervised Visual Representation Learning

  9. Predicting upcoming visual features during eye movements yields scene representations aligned with human visual cortex

    Nov 16, 2025Sushrut Thorat, Adrien Doerig, Alexander Kroner +2Predictive CodingVisual Neuroscience

  10. Φeat: Physically Grounded Material Feature Representation

    Nov 14, 2025Giuseppe Vecchio, Adrien Kaiser, Claudia Cuttano +4Representation LearningVisual Representation Learning

  11. Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMs

    Jul 1, 2025Selim Kuzucu, Muhammad Ferjad Naeem, Anna Kukleva +2Vision TransformerSelf-Supervised Visual Representation Learning

  12. 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

  13. SynCo: Synthetic Hard Negatives for Contrastive Visual Representation Learning

    Oct 3, 2024Nikos Giakoumoglou, Tania StathakiContrastive LearningHard Negative Mining

  14. Learning to Visually Connect Actions and their Effects

    Jan 19, 2024Paritosh Parmar, Eric Peh, Basura FernandoVideo ReasoningSelf-Supervised Visual Representation Learning

  15. Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

    Feb 28, 2022Paritosh Parmar, Amol Gharat, Helge RhodinContrastive LearningAction Quality Assessment