 |
    |
Context as Supervisory Signal: Discovering Objects with Predictable Context
Carl Doersch1, Abhinav Gupta1, and Alexei A. Efros2
1Carnegie Mellon University, USA
2UC Berkeley, USA
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.
Keywords: Context, prediction, unsupervised object discovery, mining
LNCS 8691, p. 362 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014