Research map / Label-efficient and robust learning / Noisy labels
Just Y-Prediction: Enabling Historical Cumulative Inconsistency in Label Diffusion for Learning with Noisy Label
Senyu Hou, Gaoxia Jiang, Xinyi Zheng, Yaqing Guo, Shuna Liang, Wenjian Wang
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 pre-correction (ablation) | JYP · CIFAR-10 Sym. 50% | accuracy: 97.01 -> 97.35 | Improved |
| add dual-view sample selection (ablation) | JYP · CIFAR-10 Sym. 50% | accuracy: 96.58 -> 97.35 | Improved |
| add HCI and dual-view on top of y-prediction baseline (ablation) | JYP · CIFAR-10 Sym. 50% | accuracy: 96.10 -> 97.35 | Improved |
| add pre-correction (ablation) | JYP · CIFAR-10 IDN 40% | accuracy: 97.26 -> 97.45 | Improved |
| add dual-view sample selection (ablation) | JYP · CIFAR-10 IDN 40% | accuracy: 96.66 -> 97.45 | Improved |
| add HCI and dual-view on top of y-prediction baseline (ablation) | JYP · CIFAR-10 IDN 40% | accuracy: 96.03 -> 97.45 | Improved |
| add all modules (pre-correction, dual-view, HCI) (ablation) | JYP · CIFAR-10 Sym. 50% | accuracy: 95.39 -> 97.35 | Improved |
| use y-prediction instead of epsilon-prediction (ablation) | label diffusion model · CIFAR-10 (50% Sym., 40% IDN, Human) | accuracy | Improved |
| use y-prediction for one-step inference instead of epsilon-prediction (ablation) | label diffusion model · CIFAR-10 noisy | one-step test accuracy | Improved |
| one-step inference (JYP) instead of iterative inference (LRAD) | JYP · WebVision | inference time: 21s to 4s | Improved |
| one-step inference (JYP) instead of iterative inference (LRAD) | JYP · ILSVRC12 | inference time: 27s to 5s | Improved |
| use dual-view strict partition in low-noise settings | JYP · CIFAR low-noise | accuracy | Hurt |
Closest papers by meaning
- Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels (NeurIPS 2023 · similarity 0.91)
- Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation (TPAMI 2026 · similarity 0.90)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.89)
- Label-Noise Robust Diffusion Models (ICLR 2024 · similarity 0.88)
- Directional Label Diffusion Model for Learning from Noisy Labels (CVPR 2025 · similarity 0.88)
- Label Noise: Ignorance Is Bliss (NeurIPS 2024 · 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.
