English

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

Computer Vision and Pattern Recognition 2023-04-20 v4 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2106.07217,
  title  = {Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels},
  author = {Seulki Park and Hwanjun Song and Daeho Um and Dae Ung Jo and Sangdoo Yun and Jin Young Choi},
  journal= {arXiv preprint arXiv:2106.07217},
  year   = {2023}
}

Comments

15 pages