Learning from massive noisy labeled data for image classification
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractLarge-scale supervised datasets are crucial to train convolutional neural networks (CNNs) for various computer vision problems. However, obtaining a massive amount of well-labeled data is usually very expensive and time consuming. In this paper, we introduce a general framework to train CNNs with only a limited number of clean labels and millions of easily obtained noisy labels. We model the relationships between images, class labels and label noises with a probabilistic graphical model and further integrate it into an end-to-end deep learning system. To demonstrate the effectiveness of our approach, we collect a large-scale real-world clothing classification dataset with both noisy and clean labels. Experiments on this dataset indicate that our approach can better correct the noisy labels and improves the performance of trained CNNs.
All Author(s) ListXiao T., Xia T., Yang Y., Huang C., Wang X.
Name of ConferenceIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Start Date of Conference07/06/2015
End Date of Conference12/06/2015
Place of ConferenceBoston
Country/Region of ConferenceUnited States of America
Volume Number07-12-June-2015
Pages2691 - 2699
LanguagesEnglish-United Kingdom

Last updated on 2021-29-01 at 00:13