mlsanityData to 14 Oct 2026

Mean Shift for Self-Supervised Learning

arXiv 2105.07269 ↗First posted 15 May 2021cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

Most recent self-supervised learning (SSL) algorithms learn features by contrasting between instances of images or by clustering the images and then contrasting between the image clusters. We introduce a simple mean-shift algorithm that learns representations by grouping images together without contrasting between them or adopting much of prior on the structure of the clusters. We simply "shift" the embedding of each image to be close to the "mean" of its neighbors. Since in our setting, the closest neighbor is always another augmentation of the same image, our model will be identical to BYOL when using only one nearest neighbor instead of 5 as used in our experiments. Our model achieves 72.4% on ImageNet linear evaluation with ResNet50 at 200 epochs outperforming BYOL. Our code is available here: https://github.com/UMBCvision/MSF

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). Builds on 40 of its 56 references that are in the map. First posted on arXiv 15 May 2021.

Builds on

40 of 56 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  11. 2013Describing Textures in the Wildcited by 2,125
  12. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
28 more
  1. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  2. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  3. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  4. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  5. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  6. 2019Contrastive Multiview Codingcited by 1,301
  7. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  8. 2016Colorful Image Colorizationcited by 1,114
  9. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  10. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  11. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  12. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  13. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  14. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  15. 2019Self-labelling via simultaneous clustering and representation learningcited by 528
  16. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  17. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 300
  18. 2016Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Predictioncited by 217
  19. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  20. 2019Local Aggregation for Unsupervised Learning of Visual Embeddingscited by 204
  21. 2017Representation Learning by Learning to Countcited by 120
  22. 2018Boosting Self-Supervised Learning via Knowledge Transfercited by 92
  23. 2019Unsupervised Deep Learning by Neighbourhood Discoverycited by 78
  24. 2020CompRess: Self-Supervised Learning by Compressing Representationscited by 62
  25. 2016CliqueCNN: Deep Unsupervised Exemplar Learningcited by 41
  26. 2020CO2: Consistent Contrast for Unsupervised Visual Representation Learningcited by 38
  27. 2020ISD: Self-Supervised Learning by Iterative Similarity Distillationcited by 33
  28. 2020Unsupervised Representation Learning by InvariancePropagationcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 22; 2023: 21; 2024: 7; 2025: 4; 2026: 2.

65 papers.

Sort:

By area:

  1. 2023A Cookbook of Self-Supervised Learningcited by 250
  2. 2022Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methodscited by 149
  3. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  4. 2021Backdoor Attacks on Self-Supervised Learningcited by 90
  5. 2021PASS: An ImageNet replacement for self-supervised pretraining without humanscited by 51
  6. 2021Improving Contrastive Learning by Visualizing Feature Transformationcited by 44
  7. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
  8. 2024Contrastive Mean-Shift Learning for Generalized Category Discoverycited by 39
  9. 2021Unsupervised Domain Generalization by Learning a Bridge Across Domainscited by 33
  10. 2022SimA: Simple Softmax-free Attention for Vision Transformerscited by 32
  11. 2022CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learningcited by 29
  12. 2024EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentationcited by 27
38 more
  1. 2022SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillationcited by 21
  2. 2023MaskCon: Masked Contrastive Learning for Coarse-Labelled Datasetcited by 21
  3. 2023Defending Against Patch-based Backdoor Attacks on Self-Supervised Learningcited by 20
  4. 2023Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learningcited by 20
  5. 2021A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervisioncited by 19
  6. 2023Audio-Visual Contrastive Learning with Temporal Self-Supervisioncited by 18
  7. 2023CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrappingcited by 17
  8. 2022Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patchescited by 16
  9. 2022Dual Contrastive Learning for Spatio-temporal Representationcited by 15
  10. 2022Self-Taught Metric Learning without Labelscited by 13
  11. 2022Adaptive Soft Contrastive Learningcited by 13
  12. 2022SERE: Exploring Feature Self-relation for Self-supervised Transformercited by 12
  13. 2023SimMatchV2: Semi-Supervised Learning with Graph Consistencycited by 12
  14. 2021Semantic-Aware Generation for Self-Supervised Visual Representation Learningcited by 11
  15. 2023All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy Reductioncited by 11
  16. 2022Localized Contrastive Learning on Graphscited by 10
  17. 2023Contextually Affinitive Neighborhood Refinery for Deep Clusteringcited by 10
  18. 2022Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learningcited by 8
  19. 2023Adaptive Multi-head Contrastive Learningcited by 8
  20. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  21. 2021Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learningcited by 7
  22. 2022Unsupervised Visual Representation Learning via Mutual Information Regularized Assignmentcited by 7
  23. 2022Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learningcited by 6
  24. 2024Contrastive Learning with Synthetic Positivescited by 6
  25. 2022Negative Selection by Clustering for Contrastive Learning in Human Activity Recognitioncited by 5
  26. 2022Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlapscited by 5
  27. 2023Meta Co-Training: Two Views are Better than Onecited by 5
  28. 2021Computer Vision Self-supervised Learning Methods on Time Seriescited by 4
  29. 2022Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Featurescited by 4
  30. 2023Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Featurescited by 4
  31. 2022Establishing a stronger baseline for lightweight contrastive modelscited by 3
  32. 2023Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learningcited by 3
  33. 2025Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machinescited by 3
  34. 2022MSR: Making Self-supervised learning Robust to Aggressive Augmentationscited by 2
  35. 2022Okapi: Generalising Better by Making Statistical Matches Matchcited by 2
  36. 2023Enhancing Representations through Heterogeneous Self-Supervised Learningcited by 2
  37. 2023Erasing Self-Supervised Learning Backdoor by Cluster Activation Maskingcited by 2
  38. 2023Rethinking Samples Selection for Contrastive Learning: Mining of Potential Samplescited by 1

50 most cited of 65 All 65 (JSON)