LOL: Learning To Optimize Loss Switching Under Label Noise

Autor: Ryuichiro Hataya, Hideki Nakayama
Rok vydání: 2019
Předmět:
Zdroj: ICIP
DOI: 10.1109/icip.2019.8803512
Popis: Deep convolutional neural networks excel in image recognition, but they are also known to be fragile to label corruption. To mitigate this problem, we propose to dynamically switch two loss functions, categorical cross entropy and mean absolute error, to exploit their complementary advantages. We employ the bilevel programming approach to simultaneously optimize base CNNs and the weights of two loss functions. Our proposed method only requires little modification in the optimization process of the original supervised problem and is applicable to a wide variety of networks under label corruption. Further, our approach achieves on-par results with other state-of-the-art noise-tolerant learning methods.
Databáze: OpenAIRE