Abstract | ||
---|---|---|
Deep learning has achieved tremendous success in image classification. However, the corresponding performance leap relies heavily on large-scale accurate annotations, which are usually hard to collect in reality. It is essential to explore methods that can train deep models effectively under label noise. To address the problem, we propose to train deep models with robust binary loss functions. To be specific, we tackle the K-class classification task by using K binary classifiers. We can immediately use multi-category large margin classification approaches, e.g., Pairwise-Comparison (PC) or One-Versus-All (OVA), to jointly train the binary classifiers for multi-category classification. Our method can be robust to label noise if symmetric functions, e.g., the sigmoid loss or the ramp loss, are employed as the binary loss function in the framework of risk minimization. The learning theory reveals that our method can be inherently tolerant to label noise in multi-category classification tasks. Extensive experiments over different datasets with different types of label noise are conducted. The experimental results clearly confirm the effectiveness of our method. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414493 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
Deep learning, image recognition, label noise, robust loss function | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Defu Liu | 1 | 0 | 2.37 |
Guowu Yang | 2 | 309 | 42.99 |
Jinzhao Wu | 3 | 8 | 4.99 |
Jiayi Zhao | 4 | 0 | 1.01 |
Fengmao Lv | 5 | 27 | 3.49 |