Rechercher

[WTC17] Gaze latent support vector machine for image classification improved by weakly supervised region selection

Revue Internationale avec comité de lecture : Journal Pattern Recognition, 2017
motcle:
Résumé: This paper deals with Weakly Supervised Learning (WSL), i.e. performing image classification by lever- aging local information with models trained from global image labels. We propose a new WSL method which incorporates gaze features collected by an eye-tracker to guide the region selection policy. Our approach presents two appealing advantages: gaze features are cheap to collect, e.g. one order of magni- tude faster than bounding boxes, and our method only requires gaze features during training, while being gaze free at test time. For this purpose, the training objective is enriched with a gaze loss, from which we derive a concave-convex upper bound, leading to an off-the-shelf CCCP optimization scheme. Extensive experiments are conducted to validate the effectiveness of the approach for WSL image classification on two public datasets with gaze annotation, i.e. PASCAL VOC 2012 action and POET. In addition, we pub- licly release a new food-related dataset, the Gaze-based UPMC Food dataset (UPMC-G20), which covers 20 food categories and 2,00 0 images. This dataset intends to promote the research in the food-related computer vision community.

BibTeX

@article {
WTC17,
title="{Gaze latent support vector machine for image classification improved by weakly supervised region selection }",
author="X. Wang and N. Thome and M. Cord",
journal="Pattern Recognition",
year=2017,
}