Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection

TL;DR

This paper proposes a collaborative training approach for region proposal and classification in two-stage object detectors to improve domain adaptation performance, addressing the domain shift challenge.

Contribution

It introduces a novel method leveraging mutual guidance and discrepancy minimization between RPN and RPC for better domain adaptive object detection.

Findings

Significant improvement in domain adaptation performance on various datasets.

Effective mutual guidance strategy between RPN and RPC.

Enhanced region proposal quality under domain shift.

Abstract

Object detectors are usually trained with large amount of labeled data, which is expensive and labor-intensive. Pre-trained detectors applied to unlabeled dataset always suffer from the difference of dataset distribution, also called domain shift. Domain adaptation for object detection tries to adapt the detector from labeled datasets to unlabeled ones for better performance. In this paper, we are the first to reveal that the region proposal network (RPN) and region proposal classifier~(RPC) in the endemic two-stage detectors (e.g., Faster RCNN) demonstrate significantly different transferability when facing large domain gap. The region classifier shows preferable performance but is limited without RPN's high-quality proposals while simple alignment in the backbone network is not effective enough for RPN adaptation. We delve into the consistency and the difference of RPN and RPC, treat them individually and leverage high-confidence output of one as mutual guidance to train the other. Moreover, the samples with low-confidence are used for discrepancy calculation between RPN and RPC and minimax optimization. Extensive experimental results on various scenarios have demonstrated the effectiveness of our proposed method in both domain-adaptive region proposal generation and object detection. Code is available at https://github.com/GanlongZhao/CST_DA_detection.