TY - JOUR

T1 - DECODE

T2 - Deep Confidence Network for Robust Image Classification

AU - Ding, Guiguang

AU - Guo, Yuchen

AU - Chen, Kai

AU - Chu, Chaoqun

AU - Han, Jungong

AU - Dai, Qionghai

N1 - ©2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

PY - 2019/8/1

Y1 - 2019/8/1

N2 - 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.

AB - 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.

KW - deep learning

KW - robustness

KW - confidence model

U2 - 10.1109/TIP.2019.2902115

DO - 10.1109/TIP.2019.2902115

M3 - Journal article

VL - 28

SP - 3752

EP - 3765

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 8

ER -