Semi-supervised robust deep neural networks for multi-label image classification
作者：
Highlights：
• Large-scale data includes many noisily labeled and unlabeled examples.
• With traditional methods, incorrect labels cause a very large loss, which misleads the training process.
• We propose to use the robust ramp function for multi-label image classification, which allows us to utilize examples with noisy labels successfully.
• In addition, the added robustness makes the method more robust against errors made during propagating labels to unlabeled examples, which allows robust semi-supervised training.
摘要
•Large-scale data includes many noisily labeled and unlabeled examples.•With traditional methods, incorrect labels cause a very large loss, which misleads the training process.•We propose to use the robust ramp function for multi-label image classification, which allows us to utilize examples with noisy labels successfully.•In addition, the added robustness makes the method more robust against errors made during propagating labels to unlabeled examples, which allows robust semi-supervised training.
论文关键词：Multi-label classification,Semi-supervised learning,Ramp loss,Image classification,Deep learning
论文评审过程：Received 6 April 2019, Revised 2 December 2019, Accepted 14 December 2019, Available online 27 December 2019, Version of Record 5 January 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.107164
