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. SEEC: A Large-Scale Dataset and Benchmark for Self-Supervised External-Eye Representation Learning

    Nov 19, 2026George R. Nahass, Michelle Fleishaker, Sanjay Ganesh +6Medical Image Representation LearningMedical Image Benchmarks

  2. Breaking Noise Shortcuts in Self-Supervised Learning Via Noise-Aligned View Generation

    Nov 19, 2026Oankar R. Patil, May D. WangSelf-Supervised Visual Representation LearningData Augmentation

  3. ReCoCo: From Patches to Compositions for Visual Representation Learning

    Nov 18, 2026Juan Gutiérrez, Saman Zadtootaghaj, José Luis Blanco-Murillo +1Visual Representation LearningSelf-Supervised Visual Representation Learning

  4. Centroid Spectral Coupling: Implicit Alignment and Representation Diversity in Self-Supervised Learning

    Nov 17, 2026M. Hadi Sepanj, Benyamin Ghojogh, Saed Moradi +1Self-Supervised LearningSelf-Supervised Visual Representation Learning

  5. Defect-Aware Masked Autoencoders for Unsupervised Clustering of Steel Surface Defects

    Nov 16, 2026Shrey PatelMasked AutoencodersUnsupervised Clustering

  6. Self-supervised learning for zebrafish embryo phenotype evaluation: Systematic comparison of algorithms, label-efficient classification, and transfer learning

    Nov 15, 2026Thomas Lautenschlager, Gaëlle Hayot, Quentin Brassart +10Self-Supervised Visual Representation LearningTransfer Learning

  7. Scaling Channel-Adaptive Self-Supervised Learning

    Nov 13, 2026Alice V. De Lorenci, Seungeun Yi, Theo Moutakanni +4Self-Supervised LearningSelf-Supervised Visual Representation Learning

  8. Where to Predict in Retinal OCT? Anatomy-Guided Target Selection for I-JEPA

    Nov 12, 2026Yunchu Feng, Wai Tak Lau, Kaveri A. ThakoorMedical Image Representation LearningSelf-Supervised Visual Representation Learning

  9. Contrastive Bootstrap Representation Learning for Label-Efficient Agricultural Image Classification

    Nov 11, 2026Hazem Ahmed, Ali Hamdi, Ammar MohammedSelf-Supervised Visual Representation LearningContrastive Learning

  10. RS-JEPA: Remote Sensing Joint-Embedding Predictive Architecture with Scan-Path Views for Cross-Sensor Image Retrieval

    Nov 10, 2026Tanishq Rachamalla, Srishti Kaushik, Muhammad Attique Khan +2Image RetrievalJoint-Embedding Predictive Architecture

  11. Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality

    Nov 9, 2026Ching Lam Choi, Antonio Torralba, Phillip Isola +1Synthetic Data PretrainingSynthetic Data Evaluation

  12. Self-Supervised Collapse Prevention with Score-Based Entropy Maximization

    Nov 8, 2026Adarsh Kappiyath, Silpa Vadakkeeveetil Sreelatha, Xiatian Zhu +3Self-Supervised Visual Representation LearningRepresentation Collapse

  13. SurgWorld: Learning Surgical Representations Beyond Observation via Latent Prediction

    Nov 8, 2026Jingkun Yue, Pengxiang Wang, Siqi Zhang +7Surgical Video UnderstandingVideo Representation Learning

  14. Self-Supervised Diffusion Models for Handwritten Signature Verification via Ruin Reconstruction

    Nov 5, 2026Peirong Zhang, Zhenhua Yang, Jiaxin Zhang +5Biometric IdentificationRepresentation Learning

  15. Representation Learning for 3D Brain Imaging: A Benchmark

    Nov 4, 2026Pierre Falconnier, Robin Trombetta, Nicolas Duchateau +1Medical Image Representation Learning3D Medical Imaging

  16. XuanJian-DINOSAR: A SAR Foundation Model Based on Global and Local Semantic Consistency

    Nov 4, 2026Chunxiao Wu, Huixin Huang, Jialei Pan +9Self-Supervised Visual Representation LearningSynthetic Aperture Radar

  17. Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses

    Nov 3, 2026Zhengtao Gao, Francesco Bombassei De Bona, Leonardo Alchieri +6Facial Expression RecognitionData-Efficient Learning

  18. Learning from Unlabeled Photographs for General Oral Image Analysis

    Nov 3, 2026Zhong-Shi Zhang, Zi-Li Yu, Xiao Xiao +4Medical Image Representation LearningMedical Image Analysis

  19. Balancing Representations by Identifying and Generating Under-represented Data

    Nov 2, 2026Filipe Laitenberger, Hirokatsu Kataoka, Yuki Asano +2Self-Supervised Visual Representation LearningLong-Tail Learning

  20. Fisher Contrastive Learning to Mitigate Feature Suppression: A Case Study in Acute Promyelocytic Leukemia Diagnosis

    Oct 29, 2026Shushan Wu, Yongkai Chen, Xilin Gong +3Contrastive LearningSelf-Supervised Visual Representation Learning

  21. Annotation-Free Representation Learning for Polyp Retrieval in Colonoscopy Videos

    Oct 29, 2026Luca Parolari, Lamberto Ballan, Carlo Biffi +1Medical Image RetrievalImage Retrieval

  22. WithinVAE: Compact Visual Autoencoding with Self-Distilled Semantics

    Oct 27, 2026Yuzhou Ji, Jiepeng Wang, Tianyu Jin +4Variational AutoencodersVisual Token Compression

  23. The Locality Trade-off in Masked Patch Self-Distillation

    Oct 23, 2026Xi Weng, Zhaoyu Liu, Lianyu Hu +1Self-Supervised Visual Representation LearningVision Foundation Models

  24. Augmentation Strategy for DINO in Glaucoma Classification

    Oct 23, 2026Ashish Kumar Meena, Chandra Sekhar SeelamantulaSelf-Supervised LearningSelf-Supervised Visual Representation Learning

  25. Representation Learning via Composite Subspace Flow Matching

    Oct 23, 2026José Afonso, Mário FigueiredoSelf-Supervised Visual Representation LearningFlow Matching

  26. IFC-SSL-Bench: Benchmarking Self-Supervised Learning for Annotation-Efficient Multispectral Imaging Flow Cytometry

    Oct 22, 2026Angelo Jovin Yamachui Sitcheu, Roxana-Teodora Fetescu, Thomas Lautenschlager +6Self-Supervised LearningSelf-Supervised Visual Representation Learning

  27. CODI: Improving Self-Supervised Vision Transformers with Cross Distillation

    Oct 22, 2026Siran Dai, Qianqian Xu, Peisong Wen +3Vision TransformerSelf-Supervised Visual Representation Learning

  28. Touch-JEPA: Tactile Representation Learning from Hand-Object Video with Limited Tactile Supervision

    Oct 20, 2026Minseong Kweon, Qiao Feng, Yiming Huang +1Visuo-Tactile Representation LearningHand-Object Interaction