Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection

TL;DR

This paper introduces Cyclic-Bootstrap Labeling (CBL), a novel weakly supervised object detection method that improves pseudo-label quality by leveraging a teacher network with rank information, leading to better detection accuracy.

Contribution

The paper proposes a new CBL framework that uses a teacher network with rank distillation to enhance pseudo-labeling in weakly supervised object detection.

Findings

Outperforms existing methods on PASCAL VOC and COCO datasets.

Improves pseudo-label accuracy through rank-based distillation.

Enhances detection performance with a novel teacher-student approach.

Abstract

Recent progress in weakly supervised object detection is featured by a combination of multiple instance detection networks (MIDN) and ordinal online refinement. However, with only image-level annotation, MIDN inevitably assigns high scores to some unexpected region proposals when generating pseudo labels. These inaccurate high-scoring region proposals will mislead the training of subsequent refinement modules and thus hamper the detection performance. In this work, we explore how to ameliorate the quality of pseudo-labeling in MIDN. Formally, we devise Cyclic-Bootstrap Labeling (CBL), a novel weakly supervised object detection pipeline, which optimizes MIDN with rank information from a reliable teacher network. Specifically, we obtain this teacher network by introducing a weighted exponential moving average strategy to take advantage of various refinement modules. A novel class-specific ranking distillation algorithm is proposed to leverage the output of weighted ensembled teacher network for distilling MIDN with rank information. As a result, MIDN is guided to assign higher scores to accurate proposals among their neighboring ones, thus benefiting the subsequent pseudo labeling. Extensive experiments on the prevalent PASCAL VOC 2007 \& 2012 and COCO datasets demonstrate the superior performance of our CBL framework. Code will be available at https://github.com/Yinyf0804/WSOD-CBL/.