Learning From Noisy Web Data With Category-Level Supervision

Li Niu, Qingtao Tang, Ashok Veeraraghavan, Ashutosh Sabharwal; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7689-7698

Abstract


Learning from web data is increasingly popular due to abundant free web resources. However, the performance gap between webly supervised learning and traditional supervised learning is still very large, due to the label noise of web data. To fill this gap, most existing methods propose to purify or augment web data using instance-level supervision, which generally requires heavy annotation. Instead, we propose to address the label noise by using more accessible category-level supervision. In particular, we build our deep probabilistic framework upon variational autoencoder (VAE), in which classification network and VAE can jointly leverage category-level hybrid information. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed method.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Niu_2018_CVPR,
author = {Niu, Li and Tang, Qingtao and Veeraraghavan, Ashok and Sabharwal, Ashutosh},
title = {Learning From Noisy Web Data With Category-Level Supervision},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}