Research map / Label-efficient and robust learning / Noisy labels
Deep Noise Label Learning via Effective Rank Reduction
Changyi Ma, Zihan Fang, Lihua Zhou, Tao Li, Wenyu Liu, Runsheng Yu, Xuan Song
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 nuclear-norm effective-rank regularization on transition matrix (ablation) | LENL · CIFAR-100N | accuracy: -4.6% accuracy when removed | Improved |
| low-effective-rank transition matrix versus PLM | LENL-NS · CIFAR-100N | accuracy: 60.52 -> 61.51 | Improved |
| LENL versus PLM/IDLE on CIFAR-100 synthetic noise | LENL-SVD · CIFAR-100 | accuracy: 69.54 -> 70.42 (Sym-20%) | Improved |
| Newton-Schulz nuclear norm instead of SVD for large class counts | LENL · ImageNet-1K | accuracy: VolMinNet fails; LENL-NS 73.35 (Sym-20%) | Improved |
| LENL-NS versus Co-Teaching on ImageNet-1K | LENL-NS · ImageNet-1K Pair-45% | accuracy: 64.08 -> 65.59 | Improved |
| LENL-NS versus CE on Food-101N | LENL-NS · Food-101N | accuracy: 80.34 -> 83.30 | Improved |
| LENL-NS versus CE on Noisy Ostracods precision | LENL-NS · Noisy Ostracods | precision: 88.50 -> 87.21 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Co-Teaching — Co-teaching: Robust training of deep neural networks with extremely noisy labels (NeurIPS 2018) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning with Feature-Dependent Label Noise: A Progressive Approach (ICLR 2021 · similarity 0.91)
- Extended : Learning with Mixed Closed-set and Open-set Noisy Labels (TPAMI 2022 · similarity 0.90)
- NoiseRank: Unsupervised Label Noise Reduction with Dependence Models (ECCV 2020 · similarity 0.90)
- Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection (ECCV 2022 · similarity 0.90)
- Noise-Robust Learning from Multiple Unsupervised Sources of Inferred Labels (AAAI 2022 · similarity 0.90)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.89)
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.
