mlsanityData to 7 Oct 2026

Learning to See by Moving

arXiv 1505.01596 ↗First posted 7 May 2015cs.CV cs.NE cs.ROcited by 101

Not on the map. Why?

Abstract (arXiv)

The dominant paradigm for feature learning in computer vision relies on training neural networks for the task of object recognition using millions of hand labelled images. Is it possible to learn useful features for a diverse set of visual tasks using any other form of supervision? In biology, living organisms developed the ability of visual perception for the purpose of moving and acting in the world. Drawing inspiration from this observation, in this work we investigate if the awareness of egomotion can be used as a supervisory signal for feature learning. As opposed to the knowledge of class labels, information about egomotion is freely available to mobile agents. We show that given the same number of training images, features learnt using egomotion as supervision compare favourably to features learnt using class-label as supervision on visual tasks of scene recognition, object recognition, visual odometry and keypoint matching.

Key facts. Cited by 101 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 May 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 26; 2023: 16; 2024: 8; 2025: 11; 2026: 4.

101 papers.

Sort:

By area:

  1. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  2. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  3. 2023A Cookbook of Self-Supervised Learningcited by 248
  4. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  5. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  6. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  7. 2026V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learningcited by 104
  8. 2021Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspectivecited by 81
  9. 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80
  10. 2022Object discovery and representation networkscited by 80
  11. 2023Advancing Radiograph Representation Learning with Masked Record Modelingcited by 75
  12. 2023Siamese Masked Autoencoderscited by 75
38 more
  1. 2021Equivariant Contrastive Learningcited by 65
  2. 2021Self-supervised Video Transformercited by 64
  3. 2021Learning Task Informed Abstractionscited by 58
  4. 2021SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representationscited by 55
  5. 2021SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistencycited by 47
  6. 2022Discovering Objects that Can Movecited by 44
  7. 2021Long-Short Temporal Contrastive Learning of Video Transformerscited by 42
  8. 2023Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled videocited by 40
  9. 2021Contrasting Contrastive Self-Supervised Representation Learning Pipelinescited by 37
  10. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  11. 2021Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networkscited by 31
  12. 2022Self-supervised Learning from 100 Million Medical Imagescited by 31
  13. 2022MeshMAE: Masked Autoencoders for 3D Mesh Data Analysiscited by 31
  14. 2021Jigsaw Clustering for Unsupervised Visual Representation Learningcited by 30
  15. 2024Scaling 4D Representationscited by 30
  16. 2021Exploring Set Similarity for Dense Self-supervised Representation Learningcited by 29
  17. 2021Self-Supervised Representation Learning from Flow Equivariancecited by 28
  18. 2022Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learningcited by 26
  19. 2021DF-VO: What Should Be Learnt for Visual Odometry?cited by 22
  20. 2022Unsupervised Visual Representation Learning by Synchronous Momentum Groupingcited by 22
  21. 2024The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learningcited by 21
  22. 2021Self-Supervised Pretraining for RGB-D Salient Object Detectioncited by 20
  23. 2022Self-supervised video pretraining yields robust and more human-aligned visual representationscited by 20
  24. 2021Contrastive Learning of Image Representations with Cross-Video Cycle-Consistencycited by 19
  25. 2021A Study of the Generalizability of Self-Supervised Representationscited by 18
  26. 2021Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learningcited by 16
  27. 2021Contextualized Spatio-Temporal Contrastive Learning with Self-Supervisioncited by 15
  28. 2021Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Visioncited by 14
  29. 2021RIO: Rotation-equivariance supervised learning of robust inertial odometrycited by 14
  30. 2023ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoderscited by 14
  31. 2021Composable Augmentation Encoding for Video Representation Learningcited by 13
  32. 2022Structural Causal 3D Reconstructioncited by 12
  33. 2022MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behaviorcited by 12
  34. 2023Self-Supervised Video Similarity Learningcited by 12
  35. 2025General Intelligence Requires Reward-based Pretrainingcited by 12
  36. 2023Flow Factorized Representation Learningcited by 11
  37. 2023Efficient Planning with Latent Diffusioncited by 11
  38. 2024PooDLe: Pooled and dense self-supervised learning from naturalistic videoscited by 11

50 most cited of 101 All 101 (JSON)