Yash Patel
Research Subjects
Yash Patel has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Dimosthenis Karatzas
Computer Vision Center
2 shared publications - Lluis Gomez
Universitat Autónoma de Barcelona
2 shared publications - Cv Jawahar
International Institute of Information Technology
1 shared publication Marçal Rusiñol
Universitat Autónoma de Barcelona
1 shared publication- Marçal Rusiñol
AllRead MLT Barcelona Spain
1 shared publication
Latest Publications
- Open Access
Self-supervised learning of visual features through embedding images into text topic spaces
End-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 multi-modal (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.
Open AccessSelf-supervised learning of visual features through embedding images into text topic spaces
End-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 multi-modal (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.
- 18 September 2016
- Published by Springer Nature
- p. 395-410
Dynamic Lexicon Generation for Natural Scene Images
- 18 September 2016
- Published by Springer Nature
- p. 395-410
Dynamic Lexicon Generation for Natural Scene Images