Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters

TL;DR

This paper introduces a novel approach to weakly-supervised object detection by learning class-agnostic bounding box adjusters from an auxiliary dataset, significantly improving localization accuracy without requiring extensive annotations.

Contribution

The paper proposes a multi-stage training framework using learnable bounding box adjusters and an EM-like algorithm, enhancing WSOD performance while avoiding auxiliary data leakage.

Findings

Outperforms state-of-the-art WSOD methods

Effective bounding box localization improvements

Cost-effective and practical implementation

Abstract

Weakly-supervised object detection (WSOD) has emerged as an inspiring recent topic to avoid expensive instance-level object annotations. However, the bounding boxes of most existing WSOD methods are mainly determined by precomputed proposals, thereby being limited in precise object localization. In this paper, we defend the problem setting for improving localization performance by leveraging the bounding box regression knowledge from a well-annotated auxiliary dataset. First, we use the well-annotated auxiliary dataset to explore a series of learnable bounding box adjusters (LBBAs) in a multi-stage training manner, which is class-agnostic. Then, only LBBAs and a weakly-annotated dataset with non-overlapped classes are used for training LBBA-boosted WSOD. As such, our LBBAs are practically more convenient and economical to implement while avoiding the leakage of the auxiliary well-annotated dataset. In particular, we formulate learning bounding box adjusters as a bi-level optimization problem and suggest an EM-like multi-stage training algorithm. Then, a multi-stage scheme is further presented for LBBA-boosted WSOD. Additionally, a masking strategy is adopted to improve proposal classification. Experimental results verify the effectiveness of our method. Our method performs favorably against state-of-the-art WSOD methods and knowledge transfer model with similar problem setting. Code is publicly available at \url{https://github.com/DongSky/lbba_boosted_wsod}.