mlsanityData to 7 Oct 2026

Contrastive Multiview Coding

arXiv 1906.05849 ↗First posted 13 Jun 2019cs.CV cs.LGcited by 1,297

Not on the map. Why?

Cited by 21 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right ear. Each view is noisy and incomplete, but important factors, such as physics, geometry, and semantics, tend to be shared between all views (e.g., a "dog" can be seen, heard, and felt). We investigate the classic hypothesis that a powerful representation is one that models view-invariant factors. We study this hypothesis under the framework of multiview contrastive learning, where we learn a representation that aims to maximize mutual information between different views of the same scene but is otherwise compact. Our approach scales to any number of views, and is view-agnostic. We analyze key properties of the approach that make it work, finding that the contrastive loss outperforms a popular alternative based on cross-view prediction, and that the more views we learn from, the better the resulting representation captures underlying scene semantics. Our approach achieves state-of-the-art results on image and video unsupervised learning benchmarks. Code is released at: http://github.com/HobbitLong/CMC/.

Key facts. Cited by 1,297 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 367; 2022: 318; 2023: 255; 2024: 167; 2025: 106; 2026: 84.

1,297 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  3. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  4. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  5. 2021Transformers in Vision: A Surveycited by 1,009
  6. 2021Model-Contrastive Federated Learningcited by 762
  7. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 626
  8. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  9. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  10. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 427
  11. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 402
  12. 2021Bottleneck Transformers for Visual Recognitioncited by 364
38 more
  1. 2024The Platonic Representation Hypothesiscited by 362
  2. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  3. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 324
  4. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  5. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  6. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 311
  7. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  8. 2025Layer by Layer: Uncovering Hidden Representations in Language Modelscited by 293
  9. 2021Graph Self-Supervised Learning: A Surveycited by 289
  10. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  11. 2021Understanding self-supervised Learning Dynamics without Contrastive Pairscited by 254
  12. 2023A Cookbook of Self-Supervised Learningcited by 248
  13. 2021Co2L: Contrastive Continual Learningcited by 243
  14. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  15. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 222
  16. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
  17. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  18. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  19. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 214
  20. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  21. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  22. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  23. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
  24. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  25. 2022Unified Contrastive Learning in Image-Text-Label Spacecited by 194
  26. 2021General Facial Representation Learning in a Visual-Linguistic Mannercited by 193
  27. 2022ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learningcited by 192
  28. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  29. 2022Dataset Condensation via Efficient Synthetic-Data Parameterizationcited by 187
  30. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 184
  31. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  32. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  33. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  34. 2023StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learnerscited by 177
  35. 2022Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlationscited by 171
  36. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 171
  37. 2022Trusted Multi-View Classification with Dynamic Evidential Fusioncited by 167
  38. 2023CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoderscited by 167

50 most cited of 1,297 All 1,297 (JSON)