Rethinking the Value of Labels for Instance-Dependent Label Noise Learning
Deng, Hanwen, Zhang, Weijia, Zhang, Min-Ling
–arXiv.org Artificial Intelligence
Label noise widely exists in large-scale datasets and significantly degenerates the performances of deep learning algorithms. Due to the non-identifiability of the instance-dependent noise transition matrix, most existing algorithms address the problem by assuming the noisy label generation process to be independent of the instance features. Unfortunately, noisy labels in real-world applications often depend on both the true label and the features. In this work, we tackle instance-dependent label noise with a novel deep generative model that avoids explicitly modeling the noise transition matrix. Our algorithm leverages casual representation learning and simultaneously identifies the high-level content and style latent factors from the data. By exploiting the supervision information of noisy labels with structural causal models, our empirical evaluations on a wide range of synthetic and real-world instance-dependent label noise datasets demonstrate that the proposed algorithm significantly outperforms the state-of-the-art counterparts.
arXiv.org Artificial Intelligence
May-14-2023
- Country:
- Oceania > Australia
- New South Wales > Callaghan (0.04)
- Asia > China
- Jiangsu Province > Nanjing (0.04)
- Oceania > Australia
- Genre:
- Research Report (0.50)
- Industry:
- Health & Medicine (0.93)
- Technology: