Research map / Label-efficient and robust learning / Noisy labels
Fine-Grained Classification With Noisy Labels
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SNSCL to DivideMix | DivideMix · Stanford Dogs, 40% symmetric noise | test accuracy: 77.93 -> 79.12 | Helped |
| Add SNSCL to DivideMix | DivideMix · Stanford Cars, 40% symmetric noise | test accuracy: 62.54 -> 80.09 | Helped |
| Add SNSCL to DivideMix | DivideMix · Aircraft, 40% symmetric noise | test accuracy: 66.76 -> 76.22 | Helped |
| Add SNSCL to DivideMix | DivideMix · CUB-200-2011, 40% symmetric noise | test accuracy: 67.35 -> 73.66 | Helped |
| Add SNSCL to DivideMix | DivideMix · Clothing-1M | test accuracy: 74.76 -> 75.31 | Helped |
| Add SNSCL to DivideMix | DivideMix · Food-101N | test accuracy: 85.88 -> 86.40 | Helped |
| Add weighted correction (ablation) | CE + SNSCL · Stanford Dogs, 40% symmetric noise | test accuracy: 70.91 -> 75.27 | Helped |
| Add weighted queue update (ablation) | CE + SNSCL · Stanford Dogs, 40% symmetric noise | test accuracy: 73.45 -> 75.27 | Helped |
| Add stochastic module (ablation) | CE + SNSCL · Stanford Dogs, 40% symmetric noise | test accuracy: 74.11 -> 75.27 | Helped |
| Add weighted correction (ablation) | DivideMix + SNSCL · CUB-200-2011, 40% symmetric noise | test accuracy: 70.41 -> 73.66 | Helped |
| Add weighted queue update (ablation) | DivideMix + SNSCL · CUB-200-2011, 40% symmetric noise | test accuracy: 72.59 -> 73.66 | Helped |
| Add stochastic module (ablation) | DivideMix + SNSCL · CUB-200-2011, 40% symmetric noise | test accuracy: 73.06 -> 73.66 | Helped |
Closest papers by meaning
- Selective-Supervised Contrastive Learning With Noisy Labels (CVPR 2022 · similarity 0.89)
- FINE Samples for Learning with Noisy Labels (NeurIPS 2021 · similarity 0.89)
- Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space (AAAI 2025 · similarity 0.88)
- Unlocking the Power of Open Set: A New Perspective for Open-Set Noisy Label Learning (AAAI 2024 · similarity 0.87)
- Learning with Structural Labels for Learning with Noisy Labels (CVPR 2024 · similarity 0.87)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.87)
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.