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

2021/06/14 by Park, Seulki, Song, Hwanjun, Um, Daeho +3
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2106.07217

Abstract

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.

Related

• Which Strategies Matter for Noisy Label Classification? Insight into Loss and Uncertainty
• Learning from Noisy Labels with Deep Neural Networks: A Survey
• Fine tuning Pre trained Models for Robustness Under Noisy Labels
• Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
• A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels