IIIT Hyderabad Publications |
|||||||||
|
Self-supervised learning of visual features through embedding images into text topic spacesAuthors: Lluis Gomez,Yash Patel,Marçal Rusiñol,Dimosthenis Karatzas, C V Jawahar Conference: IEEE Conference on Computer Vision and Pattern Recognition (CVPR-2017 2017) Date: 2017-07-21 Report no: IIIT/TR/2017/64 AbstractEnd-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multimodal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches. Full paper: pdf Centre for Visual Information Technology |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |