Context as Supervisory Signal: Discovering Objects with Predictable Context

September 2014

Context as Supervisory Signal: Discovering Objects with Predictable Context

Authors:

Carl Doersch, Abhinav Gupta, and Alexei A. Efros
Conference Paper
Proceedings of (ECCV) European Conference on Computer Vision

Abstract:

This paper addresses the well-established problem of unsupervised object discovery with a novel method inspired by weakly-supervised approaches. In particular, the ability of an object patch to predict the rest of the object (its context) is used as supervisory signal to help discover visually consistent object clusters. The main contributions of this work are: 1) framing unsupervised clustering as a leave-one-out context prediction task; 2) evaluating the quality of context prediction by statistical hypothesis testing between thing and stuff appearance models; and 3) an iterative region prediction and context alignment approach that gradually discovers a visual object cluster together with a segmentation mask and fine-grained correspondences. The proposed method outperforms previous unsupervised as well as weakly-supervised object discovery approaches, and is shown to provide correspondences detailed enough to transfer keypoint annotations.

@conference{Doersch-2014-113358,
author = {Carl Doersch And Abhinav Gupta And Alexei A. Efros},
title = {Context as Supervisory Signal: Discovering Objects with Predictable Context},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2014},
month = {September},
pages = {362 - 377},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.