Name
Abstract | ||
|---|---|---|
Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literature (with several recent exceptions) of learning with noisy labels focuses on the case when the label noise is independent from features. Practically, annotations errors tend to be instance-dependent and often depend on the difficulty levels of recognizing a certain task. Applying existing results from instance-independent settings would require a significant amount of estimation of noise rates. Therefore, learning with instance-dependent label noise remains a challenge. In this paper, we propose CORES2 (COnfidence REgularized Sample Sieve), which progressively sieves out corrupted samples. The implementation of CORES2 does not require specifying noise rates and yet we are able to provide theoretical guarantees of CORES2 in filtering out the corrupted examples. This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting. We demonstrate the performance of CORES2 on CIFAR10 and CIFAR100 datasets with synthetic instance-dependent label noise and Clothing1M with real-world human noise. As of independent interests, our sample sieve provides a generic machinery for anatomizing noisy dataset and provides flexible interface for various robust training techniques to further improve the performance. |
Year | Venue | DocType |
|---|---|---|
2021 | ICLR | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hao Cheng | 1 | 0 | 0.34 |
| Zhaowei Zhu | 2 | 0 | 0.34 |
| Xingyu Li | 3 | 11 | 3.89 |
| Yifei Gong | 4 | 1 | 3.05 |
| Sun Xing | 5 | 33 | 10.94 |
| Liu Yang | 6 | 3 | 0.70 |