.png){kind=icon}
返回
IRNet: Iterative Refinement Network for Noisy Partial Label Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TPAMI.2025.3620388.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Partial label learning (PLL) is a typical weakly supervised learning, where each sample is associated with a set of candidate labels. Its basic assumption is that the ground-truth label must be in the candidate set, but this assumption may not be satisfied due to the unprofessional judgment of annotators. Therefore, we relax this assumption and focus on a more general task, noisy PLL, where the ground-truth label may not exist in the candidate set. To address this challenging task, we propose a novel framework called “Iterative Refinement Network (IRNet)”, aiming to purify noisy samples through two key modules (i.e., noisy sample detection and label correction). To achieve better performance, we exploit smoothness constraints to reduce prediction errors in these modules. Through theoretical analysis, we prove that IRNet is able to reduce the noise level of the dataset and eventually approximate the Bayes optimal classifier. Meanwhile, IRNet is a plug-in strategy that can be integrated with existing PLL approaches. Experimental results on multiple benchmark datasets show that IRNet outperforms state-of-the-art approaches on noisy PLL.
Keyword:
Iterative refinement network (IRNet)
noisy partial label learning
noisy sample detection
label correction
multi-round refinement
期刊
IF:
18.6
论文数:
864
被引数:
9.8W
机构
引用论文
分享收藏Classification with partial labels.png)
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
OAAI
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data miningIF0
OAAI分享收藏
查看更多内容