Ding, Guiguang and Guo, Yuchen and Chen, Kai and Chu, Chaoqun and Han, Jungong and Dai, Qionghai (2019) DECODE : Deep Confidence Network for Robust Image Classification. IEEE Transactions on Image Processing, 28 (8). 3752 - 3765. ISSN 1057-7149
DCNR2.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.
Download (950kB)
Abstract
The recent years have witnessed the success of deep convolutional neural networks for image classification and many related tasks. It should be pointed out that the existing training strategies assume there is a clean dataset for model learning. In elaborately constructed benchmark datasets, deep network has yielded promising performance under the assumption. However, in real-world applications, it is burdensome and expensive to collect sufficient clean training samples. On the other hand, collecting noisy labeled samples is much economical and practical, especially with the rapidly increasing amount of visual data in theWeb. Unfortunately, the accuracy of current deep models may drop dramatically even with 5% to 10% label noise. Therefore, enabling label noise resistant classification has become a crucial issue in the data driven deep learning approaches. In this paper, we propose a DEep COnfiDEnce network, DECODE, to address this issue. In particular, based on the distribution of mislabeled data, we adopt a confidence evaluation module which is able to determine the confidence that a sample is mislabeled. With the confidence, we further use a weighting strategy to assign different weights to different samples so that the model pays less attention to low confidence data which is more likely to be noise. In this way, the deep model is more robust to label noise. DECODE is designed to be general such that it can be easily combine with existing architectures. We conduct extensive experiments on several datasets and the results validate that DECODE can improve the accuracy of deep models trained with noisy data.