Webly Supervised Learning of Convolutional Networks | IEEE Conference Publication | IEEE Xplore

Webly Supervised Learning of Convolutional Networks


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 traini...Show More

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).
Date of Conference: 07-13 December 2015
Date Added to IEEE Xplore: 18 February 2016
ISBN Information:
Electronic ISSN: 2380-7504
Conference Location: Santiago, Chile

Contact IEEE to Subscribe

References

References is not available for this document.