@inbook{f45e9fc0a01f442fb48719b642ddd14d,
title = "Self-supervised learning of visual features through embedding images into text topic spaces",
abstract = "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 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 multimodal retrieval compared to recent self-supervised or natural-supervised approaches.",
author = "Lluis Gomez and Yash Patel and Mar{\c c}al Rusinol and Dimosthenis Karatzas and Jawahar, {C. V.}",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.",
year = "2017",
month = nov,
day = "6",
doi = "10.1109/CVPR.2017.218",
language = "English",
series = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2017--2026",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
address = "United States",
}