Webly Supervised Learning of Convolutional Networks

December 2015

Webly Supervised Learning of Convolutional Networks

Authors:

Xinlei Chen and Abhinav Gupta
Conference Paper
Proceedings of (ICCV) International Conference on Computer Vision

Abstract:

We present an approach to utilize large amounts of web data for learning CNNs. Specifically inspired by curriculum learning, we present a two-step approach for CNN training. First, we use easy images to train an initial visual representation. We then use this initial CNN and adapt it to harder, more realistic images by leveraging the structure of data and categories. We demonstrate that our two-stage CNN outperforms a fine-tuned CNN trained on ImageNet on Pascal VOC 2012. We also demonstrate the strength of webly supervised learning by localizing objects in web images and training a R-CNN style [19] detector. It achieves the best performance on VOC 2007 where no VOC training data is used. Finally, we show our approach is quite robust to noise and performs comparably even when we use image search results from March 2013 (pre-CNN image search era).
@conference{Chen-2015-121555,
author = {Xinlei Chen And Abhinav Gupta},
title = {Webly Supervised Learning of Convolutional Networks},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2015},
month = {December},
pages = {1431 - 1439},
}
Copyright notice: 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. These works may not be reposted without the explicit permission of the copyright holder.