Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection

TL;DR

This paper introduces DS-MIL, a novel approach for weakly supervised object detection that finds and selects optimal solutions among multiple local minima, improving detection accuracy by capturing richer context and more informative proposals.

Contribution

The paper proposes a discovery-and-selection framework integrated with multiple instance learning, utilizing an attention module and a selection module to enhance weakly supervised object detection.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Improves detection of entire objects rather than just parts.

Enhances proposal quality with an attention-based approach.

Abstract

Weakly supervised object detection (WSOD) is a challenging task that requires simultaneously learn object classifiers and estimate object locations under the supervision of image category labels. A major line of WSOD methods roots in multiple instance learning which regards images as bags of instances and selects positive instances from each bag to learn the detector. However, a grand challenge emerges when the detector inclines to converge to discriminative parts of objects rather than the whole objects. In this paper, under the hypothesis that optimal solutions are included in local minima, we propose a discovery-and-selection approach fused with multiple instance learning (DS-MIL), which finds rich local minima and select optimal solution from multiple local minima. To implement DS-MIL, an attention module is proposed so that more context information can be captured by feature maps and more valuable proposals can be collected during training. With proposal candidates, a selection module is proposed to select informative instances for object detector. Experimental results on commonly used benchmarks show that our proposed DS-MIL approach can consistently improve the baselines, reporting state-of-the-art performance.