mlsanityData to 14 Oct 2026

Learning Visual Features from Large Weakly Supervised Data

arXiv 1511.02251 ↗First posted 6 Nov 2015cs.CVcited by 165

Not on the map. Why?

Cited by 27 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Convolutional networks trained on large supervised dataset produce visual features which form the basis for the state-of-the-art in many computer-vision problems. Further improvements of these visual features will likely require even larger manually labeled data sets, which severely limits the pace at which progress can be made. In this paper, we explore the potential of leveraging massive, weakly-labeled image collections for learning good visual features. We train convolutional networks on a dataset of 100 million Flickr photos and captions, and show that these networks produce features that perform well in a range of vision problems. We also show that the networks appropriately capture word similarity, and learn correspondences between different languages.

Key facts. Cited by 165 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2017: 1; 2018: 0; 2019: 0; 2020: 0; 2021: 42; 2022: 38; 2023: 49; 2024: 18; 2025: 12; 2026: 5.

165 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  4. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  5. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  6. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  7. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 616
  8. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 570
  9. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 561
  10. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 531
  11. 2021SLIP: Self-supervision meets Language-Image Pre-trainingcited by 436
  12. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
38 more
  1. 2022Making the Most of Text Semantics to Improve Biomedical Vision--Language Processingcited by 339
  2. 2022Is synthetic data from generative models ready for image recognition?cited by 320
  3. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
  4. 2022Prompt Distribution Learningcited by 235
  5. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  6. 2023Improving CLIP Training with Language Rewritescited by 217
  7. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 215
  8. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 198
  9. 2021Combined Scaling for Zero-shot Transfer Learningcited by 182
  10. 2021Poisoning and Backdooring Contrastive Learningcited by 151
  11. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 150
  12. 2022Multi-View Transformer for 3D Visual Groundingcited by 140
  13. 2023SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensingcited by 125
  14. 2021BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learningcited by 123
  15. 2022Task Residual for Tuning Vision-Language Modelscited by 123
  16. 2021Are Large-scale Datasets Necessary for Self-Supervised Pre-training?cited by 117
  17. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  18. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  19. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 93
  20. 2023Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Modelscited by 91
  21. 2023Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformerscited by 91
  22. 2023Image Captioners Are Scalable Vision Learners Toocited by 89
  23. 2022Touch and Go: Learning from Human-Collected Vision and Touchcited by 87
  24. 2021Multi-Label Learning from Single Positive Labelscited by 81
  25. 2024DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignmentcited by 79
  26. 2021The Shape of Learning Curves: a Reviewcited by 70
  27. 2017Hard Mixtures of Experts for Large Scale Weakly Supervised Visioncited by 67
  28. 2023BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIPcited by 67
  29. 2021Learning to Generate Scene Graph from Natural Language Supervisioncited by 64
  30. 2024A Comprehensive Survey of Foundation Models in Medicinecited by 56
  31. 2022Motion Policy Networkscited by 55
  32. 2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
  33. 2022P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervisioncited by 52
  34. 2022Multitask Vision-Language Prompt Tuningcited by 51
  35. 2023Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Promptscited by 50
  36. 2024Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understandingcited by 49
  37. 2021Structured Semantic Transfer for Multi-Label Recognition with Partial Labelscited by 41
  38. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39

50 most cited of 165 All 165 (JSON)