Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection

TL;DR

This paper introduces a weakly supervised foreground learning approach that improves object localization and detection by generating pseudo masks without additional annotations, achieving state-of-the-art results.

Contribution

The paper proposes a novel WSFL pipeline that enhances WSOL and WSOD by using foreground masks, with low computational cost and no need for localization annotations.

Findings

Achieves 72.97% localization accuracy on CUB

Attains 55.7% mAP on VOC07

Establishes new state-of-the-art results

Abstract

Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy. Hence, weakly supervised tasks, including weakly supervised object localization~(WSOL) and detection~(WSOD), have recently received attention in the computer vision community. In this paper, we motivate and propose the weakly supervised foreground learning (WSFL) task by showing that both WSOL and WSOD can be greatly improved if groundtruth foreground masks are available. More importantly, we propose a complete WSFL pipeline with low computational cost, which generates pseudo boxes, learns foreground masks, and does not need any localization annotations. With the help of foreground masks predicted by our WSFL model, we achieve 72.97% correct localization accuracy on CUB for WSOL, and 55.7% mean average precision on VOC07 for WSOD, thereby establish new state-of-the-art for both tasks. Our WSFL model also shows excellent transfer ability.