Research map / Label-efficient and robust learning / Recognition and long-tail
Learning From Large-Scale Noisy Web Data With Ubiquitous Reweighting for Image Classification
Jia Li, Yafei Song, Jianfeng Zhu, Lele Cheng, Ying Ming Su, Lin Ye, Pengcheng Yuan, Shumin Han
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add class reweighting (ablation) | baseline ResNeXt-101 · WebVision 2018 val | top-5 accuracy: 71.7% -> 72.8% | Improved |
| add cluster reweighting (ablation) | URNet · WebVision 2018 val | top-5 accuracy: 72.8% -> 75.3% | Improved |
| add instance confidence reweighting (ablation) | URNet · WebVision 2018 val | top-5 accuracy: 75.3% -> 76% | Improved |
| add bag-specific saliency reweighting (ablation) | URNet · WebVision 2018 val | top-5 accuracy: 76% -> 76.3% | Improved |
| add label reweighting (ablation) | URNet · WebVision 2018 val | top-5 accuracy: 76.3% -> 76.5% | Improved |
| keep only top 15 Flickr instances per class | URNet · WebVision 2018 val | top-5 accuracy: 76.5% -> 77.0% | Improved |
| ensemble 29 models | URNet · WebVision 2018 val | top-5 accuracy: 77.0% -> 78.3% | Improved |
| add multi-crop testing | URNet · WebVision 2018 val | top-5 accuracy: 78.3% -> 79.3% | Improved |
| add multi-scale testing | URNet · WebVision 2018 val | top-5 accuracy: 79.3% -> 79.8% | Improved |
Closest papers by meaning
- CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images (ECCV 2018 · similarity 0.86)
- Weakly Supervised Learning with Side Information for Noisy Labeled Images (ECCV 2020 · similarity 0.85)
- Learning From Web Data With Self-Organizing Memory Module (CVPR 2020 · similarity 0.85)
- Attend in Groups: A Weakly-Supervised Deep Learning Framework for Learning From Web Data (CVPR 2017 · similarity 0.85)
- REDUCR: Robust Data Downsampling using Class Priority Reweighting (NeurIPS 2024 · similarity 0.83)
- Improving Generalization via Meta-Learning on Hard Samples (CVPR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
