DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment

TL;DR

This paper introduces DATR, a novel unsupervised domain adaptive detection transformer that employs class-wise prototypes and dataset-level alignment to improve object detection across different domains, achieving superior results.

Contribution

The paper proposes a new DETR-based detector with class-aware prototype alignment and dataset-level contrastive learning for better domain adaptation in object detection.

Findings

Outperforms existing methods in multiple domain adaptation scenarios.

Effectively aligns features across domains at class and dataset levels.

Enhances generalization and detection accuracy in real-world applications.

Abstract

Object detectors frequently encounter significant performance degradation when confronted with domain gaps between collected data (source domain) and data from real-world applications (target domain). To address this task, numerous unsupervised domain adaptive detectors have been proposed, leveraging carefully designed feature alignment techniques. However, these techniques primarily align instance-level features in a class-agnostic manner, overlooking the differences between extracted features from different categories, which results in only limited improvement. Furthermore, the scope of current alignment modules is often restricted to a limited batch of images, failing to learn the entire dataset-level cues, thereby severely constraining the detector's generalization ability to the target domain. To this end, we introduce a strong DETR-based detector named Domain Adaptive detection TRansformer (DATR) for unsupervised domain adaptation of object detection. Firstly, we propose the Class-wise Prototypes Alignment (CPA) module, which effectively aligns cross-domain features in a class-aware manner by bridging the gap between object detection task and domain adaptation task. Then, the designed Dataset-level Alignment Scheme (DAS) explicitly guides the detector to achieve global representation and enhance inter-class distinguishability of instance-level features across the entire dataset, which spans both domains, by leveraging contrastive learning. Moreover, DATR incorporates a mean-teacher based self-training framework, utilizing pseudo-labels generated by the teacher model to further mitigate domain bias. Extensive experimental results demonstrate superior performance and generalization capabilities of our proposed DATR in multiple domain adaptation scenarios. Code is released at https://github.com/h751410234/DATR.