mlsanityData to 7 Oct 2026

Webly Supervised Learning of Convolutional Networks

arXiv 1505.01554 ↗First posted 7 May 2015cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

We present an approach to utilize large amounts of web data for learning CNNs. Specifically inspired by curriculum learning, we present a two-step approach for CNN training. First, we use easy images to train an initial visual representation. We then use this initial CNN and adapt it to harder, more realistic images by leveraging the structure of data and categories. We demonstrate that our two-stage CNN outperforms a fine-tuned CNN trained on ImageNet on Pascal VOC 2012. We also demonstrate the strength of webly supervised learning by localizing objects in web images and training a R-CNN style detector. It achieves the best performance on VOC 2007 where no VOC training data is used. Finally, we show our approach is quite robust to noise and performs comparably even when we use image search results from March 2013 (pre-CNN image search era).

Key facts. Cited by 95 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: 2017: 1; 2018: 0; 2019: 0; 2020: 0; 2021: 24; 2022: 22; 2023: 26; 2024: 14; 2025: 6; 2026: 2.

95 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  3. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 612
  4. 2021Curriculum Learning: A Surveycited by 257
  5. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 149
  6. 2022Robust Training under Label Noise by Over-parameterizationcited by 93
  7. 2023Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformerscited by 91
  8. 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
  9. 2021RECALL: Replay-based Continual Learning in Semantic Segmentationcited by 83
  10. 2017Hard Mixtures of Experts for Large Scale Weakly Supervised Visioncited by 67
  11. 2021Learning to Generate Scene Graph from Natural Language Supervisioncited by 64
  12. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
38 more
  1. 2021Sample Selection for Fair and Robust Trainingcited by 48
  2. 2022Webly Supervised Concept Expansion for General Purpose Vision Modelscited by 45
  3. 2022EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbonescited by 42
  4. 2021Contrastive Learning Improves Model Robustness Under Label Noisecited by 36
  5. 2021Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approachcited by 32
  6. 2023Contrastive Feature Masking Open-Vocabulary Vision Transformercited by 31
  7. 2021An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wildcited by 30
  8. 2021WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentationcited by 25
  9. 2022No Token Left Behind: Explainability-Aided Image Classification and Generationcited by 25
  10. 2022Noise-aware Learning from Web-crawled Image-Text Data for Image Captioningcited by 22
  11. 2023Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputscited by 22
  12. 2023Internet Explorer: Targeted Representation Learning on the Open Webcited by 21
  13. 2023CL-MAE: Curriculum-Learned Masked Autoencoderscited by 21
  14. 2022FUN-SIS: a Fully UNsupervised approach for Surgical Instrument Segmentationcited by 20
  15. 2022Identifying Hard Noise in Long-Tailed Sample Distributioncited by 19
  16. 2023SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labelscited by 19
  17. 2023Domain Generalization via Balancing Training Difficulty and Model Capabilitycited by 19
  18. 2021Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noisecited by 18
  19. 2023GeoNet: Benchmarking Unsupervised Adaptation across Geographiescited by 17
  20. 2022SelfD: Self-Learning Large-Scale Driving Policies From the Webcited by 16
  21. 2023RECLIP: Resource-efficient CLIP by Training with Small Imagescited by 16
  22. 2024EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Trainingcited by 16
  23. 2022Scalable Penalized Regression for Noise Detection in Learning with Noisy Labelscited by 15
  24. 2021Searching for Robustness: Loss Learning for Noisy Classification Taskscited by 13
  25. 2024Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary casescited by 13
  26. 2021Learning to Rectify for Robust Learning with Noisy Labelscited by 12
  27. 2023Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learningcited by 12
  28. 2023SYNAuG: Exploiting Synthetic Data for Data Imbalance Problemscited by 12
  29. 2021EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modelingcited by 10
  30. 2022Learning Rate Curriculumcited by 9
  31. 2022Learning to Learn: How to Continuously Teach Humans and Machinescited by 9
  32. 2022Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Featurescited by 9
  33. 2024Noisy Label Processing for Classification: A Surveycited by 8
  34. 2024Learning Discriminative Dynamics with Label Corruption for Noisy Label Detectioncited by 8
  35. 2023Reverse Stable Diffusion: What prompt was used to generate this image?cited by 7
  36. 2021Truth Discovery in Sequence Labels from Crowdscited by 6
  37. 2023Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimizationcited by 6
  38. 2023Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systemscited by 6

50 most cited of 95 All 95 (JSON)