Foreground Clustering for Joint Segmentation and Localization in Videos and Images

TL;DR

This paper introduces a unified weakly supervised framework that jointly performs segmentation and localization in videos and images by integrating appearance and high-level cues through a novel optimization approach.

Contribution

It presents a new joint optimization framework that combines low-level appearance, high-level localization cues, and a foreground model to improve segmentation and localization in videos and images.

Findings

Effective on YouTube Object dataset

Improves localization accuracy

Enhances segmentation quality

Abstract

This paper presents a novel framework in which video/image segmentation and localization are cast into a single optimization problem that integrates information from low level appearance cues with that of high level localization cues in a very weakly supervised manner. The proposed framework leverages two representations at different levels, exploits the spatial relationship between bounding boxes and superpixels as linear constraints and simultaneously discriminates between foreground and background at bounding box and superpixel level. Different from previous approaches that mainly rely on discriminative clustering, we incorporate a foreground model that minimizes the histogram difference of an object across all image frames. Exploiting the geometric relation between the superpixels and bounding boxes enables the transfer of segmentation cues to improve localization output and vice-versa. Inclusion of the foreground model generalizes our discriminative framework to video data where the background tends to be similar and thus, not discriminative. We demonstrate the effectiveness of our unified framework on the YouTube Object video dataset, Internet Object Discovery dataset and Pascal VOC 2007.