mlsanityData to 14 Oct 2026

Pixel-level Correspondence for Self-Supervised Learning from Video

arXiv 2207.03866 ↗First posted 8 Jul 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision. To address this, we propose Pixel-level Correspondence (PiCo), a method for dense contrastive learning from video. By tracking points with optical flow, we obtain a correspondence map which can be used to match local features at different points in time. We validate PiCo on standard benchmarks, outperforming self-supervised baselines on multiple dense prediction tasks, without compromising performance on image classification.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 60 of its 79 references that are in the map. First posted on arXiv 8 Jul 2022.

Builds on

60 of 79 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2017Mask R-CNNcited by 7,277
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  11. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
38 more
  1. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  2. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  3. 2017The Kinetics Human Action Video Datasetcited by 1,909
  4. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  5. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  6. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  7. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  8. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  9. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  10. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  11. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  12. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  13. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  14. 2019Panoptic Feature Pyramid Networkscited by 645
  15. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  16. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  17. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
  18. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 300
  19. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  20. 2017Dilated Residual Networkscited by 294
  21. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  22. 2019Revisiting Self-Supervised Visual Representation Learningcited by 251
  23. 2021Contrastive Learning Inverts the Data Generating Processcited by 221
  24. 2019Scaling and Benchmarking Self-Supervised Visual Representation Learningcited by 201
  25. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 198
  26. 2020TransNet V2: An effective deep network architecture for fast shot transition detectioncited by 171
  27. 2018Tracking Emerges by Colorizing Videoscited by 166
  28. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 160
  29. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  30. 2020Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biasescited by 143
  31. 2020Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Codingcited by 122
  32. 2015Learning to See by Movingcited by 102
  33. 2021Region Similarity Representation Learningcited by 96
  34. 2020Watching the World Go By: Representation Learning from Unlabeled Videoscited by 59
  35. 2015Learning visual groups from co-occurrences in space and timecited by 42
  36. 2021Video Contrastive Learning with Global Contextcited by 41
  37. 2022Point-Level Region Contrast for Object Detection Pre-Trainingcited by 41
  38. 2017Transitive Invariance for Self-supervised Visual Representation Learningcited by 37

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1; 2026: 1.

3 papers.

  1. 2022Self-supervised video pretraining yields robust and more human-aligned visual representationscited by 20
  2. 2025Pixel Motion as Universal Representation for Robot Controlcited by 15
  3. 2026Future Optical Flow Prediction Improves Robot Control & Video Generationcited by 7