Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels

arxiv(2023)

引用 0|浏览6
暂无评分
摘要
Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model. To overcome this issue, we propose a new approach for learning from noisy labels (LNL) via post-training, which can significantly improve the generalization performance of any pre-trained model on noisy label data. To this end, we rather exploit the overfitting property of a trained model to identify mislabeled samples. Specifically, our post-training approach gradually removes samples with high influence on the decision boundary and refines the decision boundary to improve generalization performance. Our post-training approach creates great synergies when combined with the existing LNL methods. Experimental results on various real-world and synthetic benchmark datasets demonstrate the validity of our approach in diverse realistic scenarios.
更多
查看译文
关键词
overfitted model property,detection,over-fit,noisy-label
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要