mlsanityData to 7 Oct 2026

Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination

arXiv 1805.01978 ↗First posted 5 May 2018cs.CV cs.LGcited by 1,838

Not on the map. Why?

Abstract (arXiv)

Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether this observation can be extended beyond the conventional domain of supervised learning: Can we learn a good feature representation that captures apparent similarity among instances, instead of classes, by merely asking the feature to be discriminative of individual instances? We formulate this intuition as a non-parametric classification problem at the instance-level, and use noise-contrastive estimation to tackle the computational challenges imposed by the large number of instance classes. Our experimental results demonstrate that, under unsupervised learning settings, our method surpasses the state-of-the-art on ImageNet classification by a large margin. Our method is also remarkable for consistently improving test performance with more training data and better network architectures. By fine-tuning the learned feature, we further obtain competitive results for semi-supervised learning and object detection tasks. Our non-parametric model is highly compact: With 128 features per image, our method requires only 600MB storage for a million images, enabling fast nearest neighbour retrieval at the run time.

Key facts. Cited by 1,838 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 452; 2022: 480; 2023: 421; 2024: 245; 2025: 167; 2026: 73.

1,838 papers.

Sort:

By area:

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  5. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  6. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  7. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  8. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  9. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  10. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 982
  11. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  12. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
38 more
  1. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  2. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 564
  3. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 516
  4. 2022Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Taskscited by 510
  5. 2024Revisiting Feature Prediction for Learning Visual Representations from Videocited by 490
  6. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  7. 2022InternVideo: General Video Foundation Models via Generative and Discriminative Learningcited by 441
  8. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 427
  9. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
  10. 2021CRIS: CLIP-Driven Referring Image Segmentationcited by 353
  11. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 324
  12. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  13. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  14. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 311
  15. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 310
  16. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  17. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 302
  18. 2022Masked Siamese Networks for Label-Efficient Learningcited by 301
  19. 2022Context Autoencoder for Self-Supervised Representation Learningcited by 297
  20. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  21. 2022The Forward-Forward Algorithm: Some Preliminary Investigationscited by 262
  22. 2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
  23. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  24. 2023A Cookbook of Self-Supervised Learningcited by 248
  25. 2022Masked Visual Pre-training for Motor Controlcited by 246
  26. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  27. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  28. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  29. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
  30. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  31. 2021Parametric Contrastive Learningcited by 217
  32. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 214
  33. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  34. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  35. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 197
  36. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  37. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  38. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186

50 most cited of 1,838 All 1,838 (JSON)