LOL: Learning To Optimize Loss Switching Under Label Noise
| Autor: | Ryuichiro Hataya, Hideki Nakayama |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Noise measurement
Computer science 02 engineering and technology 010501 environmental sciences 01 natural sciences Bilevel optimization Convolutional neural network Cross entropy Robustness (computer science) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Categorical variable Algorithm 0105 earth and related environmental sciences |
| 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 |
| Externí odkaz: |
|