mlsanityData to 7 Oct 2026

Representation Learning by Learning to Count

arXiv 1708.06734 ↗First posted 22 Aug 2017cs.CVcited by 120

Not on the map. Why?

Abstract (arXiv)

We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation. We relate transformations of images to transformations of the representations. More specifically, we look for the representation that satisfies such relation rather than the transformations that match a given representation. In this paper, we use two image transformations in the context of counting: scaling and tiling. The first transformation exploits the fact that the number of visual primitives should be invariant to scale. The second transformation allows us to equate the total number of visual primitives in each tile to that in the whole image. These two transformations are combined in one constraint and used to train a neural network with a contrastive loss. The proposed task produces representations that perform on par or exceed the state of the art in transfer learning benchmarks.

Key facts. Cited by 120 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 54; 2022: 34; 2023: 19; 2024: 6; 2025: 5; 2026: 2.

120 papers.

Sort:

By area:

  1. 2021Robust fine-tuning of zero-shot modelscited by 785
  2. 2023A Cookbook of Self-Supervised Learningcited by 248
  3. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  4. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  5. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  6. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  7. 2021Efficient Training of Visual Transformers with Small Datasetscited by 107
  8. 2021Pre-training without Natural Imagescited by 100
  9. 2021Large-scale Unsupervised Semantic Segmentationcited by 98
  10. 2022Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learningcited by 93
  11. 2022My View is the Best View: Procedure Learning from Egocentric Videoscited by 81
  12. 2021Unsupervised Object-Level Representation Learning from Scene Imagescited by 72
38 more
  1. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  2. 2022Masked Frequency Modeling for Self-Supervised Visual Pre-Trainingcited by 70
  3. 2021Mean Shift for Self-Supervised Learningcited by 65
  4. 2021Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contextscited by 59
  5. 2024Scaling Wearable Foundation Modelscited by 57
  6. 2022UniCLIP: Unified Framework for Contrastive Language-Image Pre-trainingcited by 54
  7. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  8. 2021Unsupervised Action Segmentation by Joint Representation Learning and Online Clusteringcited by 48
  9. 2021Learning by Aligning Videos in Timecited by 47
  10. 2022SimPer: Simple Self-Supervised Learning of Periodic Targetscited by 44
  11. 2022HCSC: Hierarchical Contrastive Selective Codingcited by 43
  12. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
  13. 2021Contrasting Contrastive Self-Supervised Representation Learning Pipelinescited by 37
  14. 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
  15. 2021Can Vision Transformers Learn without Natural Images?cited by 32
  16. 2021Self-Supervised Representation Learning from Flow Equivariancecited by 28
  17. 2021Self-Supervised Video Representation Learning with Meta-Contrastive Networkcited by 28
  18. 2021Self-supervised Contrastive Learning of Multi-view Facial Expressionscited by 23
  19. 2022Facial Video-based Remote Physiological Measurement via Self-supervised Learningcited by 22
  20. 2021Long Short View Feature Decomposition via Contrastive Video Representation Learningcited by 21
  21. 2022SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillationcited by 21
  22. 2021Learning to Align Sequential Actions in the Wildcited by 19
  23. 2021Consistent Explanations by Contrastive Learningcited by 18
  24. 2021Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learningcited by 18
  25. 2022Multi-scale frequency separation network for image deblurringcited by 18
  26. 2021Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrologycited by 15
  27. 2021A Simple Baseline for Low-Budget Active Learningcited by 15
  28. 2021Generative Modeling for Multi-task Visual Learningcited by 14
  29. 2022SCVRL: Shuffled Contrastive Video Representation Learningcited by 14
  30. 2022Contrastive Representation Learning for Gaze Estimationcited by 14
  31. 2021Unsupervised Two-Stage Anomaly Detectioncited by 12
  32. 2022SERE: Exploring Feature Self-relation for Self-supervised Transformercited by 12
  33. 2021Spatiotemporal Contrastive Learning of Facial Expressions in Videoscited by 11
  34. 2025Joint Self-Supervised Video Alignment and Action Segmentationcited by 11
  35. 2021Resolution-Based Distillation for Efficient Histology Image Classificationcited by 10
  36. 2021MaCLR: Motion-aware Contrastive Learning of Representations for Videoscited by 10
  37. 2021ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasetscited by 9
  38. 2023A Holistic Assessment of the Reliability of Machine Learning Systemscited by 9

50 most cited of 120 All 120 (JSON)