# Self-supervised learning of visual features through embedding images into text topic spaces Source: [Self-supervised learning of visual features through embedding images into text topic spaces]() Collection index: [llms.txt]() Data updated: 2025-10-27T05:52:51.467Z Authors: Lluis Gomez, Yash Patel, Mar\\c{c}al Rusi\\~nol, Dimosthenis Karatzas, C.V. Jawahar Published: 2017-05-24T06:59:30.000Z ## 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 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()