Publications

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication


Year(s) from:  to 
Author:
Keywords (separated by spaces):

Visual Recognition by Learning from Web Data via Weakly Supervised Domain Generalization

Li Niu, Wen Li, Dong Xu, and Jianfei Cai
IEEE Transactions on Neural Networks and Learning System (T-NNLS)
2016, in press

Abstract

In this paper, a weakly supervised domain generalization (WSDG) method is proposed for real-world visual recognition tasks, in which we train classifiers by using Web data (e.g., Web images and Web videos) with noisy labels. In particular, two challenging problems need to be solved when learning robust classifiers, in which the first issue is to cope with the label noise of training Web data from the source domain, while the second issue is to enhance the generalization capability of learned classifiers to an arbitrary target domain. In order to handle the first problem, the training samples within each category are partitioned into clusters, where we use one bag to denote each cluster and instances to denote the samples in each cluster. Then, we identify a proportion of good training samples in each bag and train robust classifiers by using the good training samples, which leads to a multi-instance learning (MIL) problem. In order to handle the second problem, we assume that the training samples possibly form a set of hidden domains, with each hidden domain associated with a distinctive data distribution. Then, for each category and each hidden latent domain, we propose to learn one classifier by extending our MIL formulation, which leads to our WSDG approach. In the testing stage, our approach can obtain better generalization capability by effectively integrating multiple classifiers from different latent domains in each category. Moreover, our WSDG approach is further extended to utilize additional textual descriptions associated with Web data as privileged information (PI), although testing data do not have such PI. Extensive experiments on three benchmark data sets indicate that our newly proposed methods are effective for real-world visual recognition tasks by learning from Web data.


Link to publisher's page
@Article{eth_biwi_01351,
  author = {Li Niu and Wen Li and Dong Xu and and Jianfei Cai},
  title = {Visual Recognition by Learning from Web Data via Weakly Supervised Domain Generalization},
  journal = {IEEE Transactions on Neural Networks and Learning System (T-NNLS)},
  year = {2016},
  month = {},
  pages = {},
  volume = {},
  number = {},
  keywords = {},
  note = {in press}
}