TY  - CONF
AU  - Lluis Gomez
AU  - Y. Patel
AU  - Marçal Rusiñol
AU  - C.V. Jawahar
AU  - Dimosthenis Karatzas
A2  - CVPR
PY  - 2017//
TI  - Self‐supervised learning of visual features through embedding images into text topic spaces
BT  - 30th IEEE Conference on Computer Vision and Pattern Recognition
N2  - 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.
UR  - https://arxiv.org/abs/1705.08631
L1  - http://refbase.cvc.uab.es/files/GPR2017.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2017.218
N1  - DAG; 600.084; 600.121
ID  - Lluis Gomez2017
ER  -