mlsanityData to 14 Oct 2026

Unsupervised Representation Learning by Predicting Image Rotations

arXiv 1803.07728 ↗First posted 21 Mar 2018cs.CV cs.LGcited by 1,591

Not on the map. Why?

Cited by 41 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic feature learning, i.e., learning without requiring manual annotation effort, is of crucial importance in order to successfully harvest the vast amount of visual data that are available today. In our work we propose to learn image features by training ConvNets to recognize the 2d rotation that is applied to the image that it gets as input. We demonstrate both qualitatively and quantitatively that this apparently simple task actually provides a very powerful supervisory signal for semantic feature learning. We exhaustively evaluate our method in various unsupervised feature learning benchmarks and we exhibit in all of them state-of-the-art performance. Specifically, our results on those benchmarks demonstrate dramatic improvements w.r.t. prior state-of-the-art approaches in unsupervised representation learning and thus significantly close the gap with supervised feature learning. For instance, in PASCAL VOC 2007 detection task our unsupervised pre-trained AlexNet model achieves the state-of-the-art (among unsupervised methods) mAP of 54.4% that is only 2.4 points lower from the supervised case. We get similarly striking results when we transfer our unsupervised learned features on various other tasks, such as ImageNet classification, PASCAL classification, PASCAL segmentation, and CIFAR-10 classification. The code and models of our paper will be published on: https://github.com/gidariss/FeatureLearningRotNet .

Key facts. Cited by 1,591 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 467; 2022: 442; 2023: 311; 2024: 195; 2025: 124; 2026: 52.

1,591 papers.

Sort:

By area:

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  4. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  5. 2021Transformers in Vision: A Surveycited by 1,013
  6. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 903
  7. 2021Robust fine-tuning of zero-shot modelscited by 797
  8. 2021Domain Generalization: A Surveycited by 764
  9. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  10. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
  11. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  12. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
38 more
  1. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 429
  2. 2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 422
  3. 2021Deep Long-Tailed Learning: A Surveycited by 417
  4. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
  5. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  6. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 372
  7. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  8. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 345
  9. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 326
  10. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  11. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  12. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  13. 2022Contrastive Test-Time Adaptationcited by 261
  14. 2021A Survey on Deep Semi-supervised Learningcited by 251
  15. 2023A Cookbook of Self-Supervised Learningcited by 250
  16. 2022Masked Visual Pre-training for Motor Controlcited by 248
  17. 2022Real-World Robot Learning with Masked Visual Pre-trainingcited by 245
  18. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  19. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  20. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  21. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 227
  22. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 215
  23. 2022Test-Time Training with Masked Autoencoderscited by 212
  24. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 207
  25. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  26. 2021ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Predictioncited by 204
  27. 2021General Facial Representation Learning in a Visual-Linguistic Mannercited by 195
  28. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  29. 2021Reinforcement Learning with Prototypical Representationscited by 179
  30. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  31. 2021BEVT: BERT Pretraining of Video Transformerscited by 169
  32. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 168
  33. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 166
  34. 2021Open-World Semi-Supervised Learningcited by 165
  35. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 160
  36. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 156
  37. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  38. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 154

50 most cited of 1,591 All 1,591 (JSON)