Research map / Label-efficient and robust learning / Noisy labels
Joint Negative and Positive Learning for Noisy Labels
Youngdong Kim, Juseung Yun, Hyounguk Shon, Junmo Kim
Check 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 |
|---|---|---|---|
| Replace NL with NL+ (ablation) | JNPL noisy-label filtering · CIFAR10 with varied noise types and rates | convergence | Improved |
| Add PL+ alongside NL+ in a single stage (ablation) | JNPL · CIFAR10 with 60% symm noise | training speed | Improved |
| Use NL+ and PL+ together instead of NLNL's three-stage pipeline (ablation) | JNPL · CIFAR10 with 60% symm noise | accuracy | Improved |
| Use NL+ instead of NL followed by SelNL (ablation) | noisy-label filtering · CIFAR10 with 40% asymm noise, cat/dog confusion | filtering effectiveness | Improved |
| Set the PL+ exponent parameter to N=3 (ablation) | PL+ · PL+ training | training results | Improved |
| Use JNPL rather than NLNL | noisy-label filtering · CIFAR10 and CIFAR100, varied noise types and rates | average precision | Improved |
| Use JNPL rather than competing baselines | noisy-label classification · CIFAR10 and CIFAR100, varied noise types and rates | accuracy | Mixed |
| Use JNPL rather than other Clothing1M baselines | noisy-label classification · Clothing1M | test accuracy | Improved |
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 2 of 3 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
- NLNL: Negative Learning for Noisy Labels (ICCV 2019 · similarity 0.95)
- BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning (TPAMI 2024 · similarity 0.89)
- Joint Optimization Framework for Learning With Noisy Labels (CVPR 2018 · similarity 0.88)
- Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks (NeurIPS 2017 · similarity 0.88)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.88)
- Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization (CVPR 2020 · similarity 0.88)
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.
