# Webly Supervised Learning of Convolutional Networks

arXiv: https://arxiv.org/abs/1505.01554 · HTML: https://mlsanity.com/paper/1505.01554/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2015.

## Built on by (most cited first, 30 of 95)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models](https://mlsanity.com/paper/2209.15639/) (2022)
- [Robust Training under Label Noise by Over-parameterization](https://mlsanity.com/paper/2202.14026/) (2022)
- [Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2305.07011/) (2023)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [RECALL: Replay-based Continual Learning in Semantic Segmentation](https://mlsanity.com/paper/2108.03673/) (2021)
- [Hard Mixtures of Experts for Large Scale Weakly Supervised Vision](https://mlsanity.com/paper/1704.06363/) (2017)
- [Learning to Generate Scene Graph from Natural Language Supervision](https://mlsanity.com/paper/2109.02227/) (2021)
- [Open-set Label Noise Can Improve Robustness Against Inherent Label Noise](https://mlsanity.com/paper/2106.10891/) (2021)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Webly Supervised Concept Expansion for General Purpose Vision Models](https://mlsanity.com/paper/2202.02317/) (2022)
- [EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones](https://mlsanity.com/paper/2211.09703/) (2022)
- [Contrastive Learning Improves Model Robustness Under Label Noise](https://mlsanity.com/paper/2104.08984/) (2021)
- [Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach](https://mlsanity.com/paper/2108.02399/) (2021)
- [Contrastive Feature Masking Open-Vocabulary Vision Transformer](https://mlsanity.com/paper/2309.00775/) (2023)
- [An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild](https://mlsanity.com/paper/2106.15610/) (2021)
- [WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation](https://mlsanity.com/paper/2109.14196/) (2021)
- [No Token Left Behind: Explainability-Aided Image Classification and Generation](https://mlsanity.com/paper/2204.04908/) (2022)
- [Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning](https://mlsanity.com/paper/2212.13563/) (2022)
- [Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs](https://mlsanity.com/paper/2306.16921/) (2023)
- [CL-MAE: Curriculum-Learned Masked Autoencoders](https://mlsanity.com/paper/2308.16572/) (2023)
- [Internet Explorer: Targeted Representation Learning on the Open Web](https://mlsanity.com/paper/2302.14051/) (2023)
- [FUN-SIS: a Fully UNsupervised approach for Surgical Instrument Segmentation](https://mlsanity.com/paper/2202.08141/) (2022)
- [Domain Generalization via Balancing Training Difficulty and Model Capability](https://mlsanity.com/paper/2309.00844/) (2023)
- [Identifying Hard Noise in Long-Tailed Sample Distribution](https://mlsanity.com/paper/2207.13378/) (2022)
- [SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels](https://mlsanity.com/paper/2308.12064/) (2023)
- [Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise](https://mlsanity.com/paper/2112.02960/) (2021)

## 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).