cs.CVJul 27, 2021

Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

Authors: Wen Wang, Yang Cao, Jing Zhang, Fengxiang He, Zheng-Jun Zha, Yonggang Wen, Dacheng Tao

Organizations: University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · The University of Sydney · JD Explore Academy, China · 

Abstract

Detection transformers have recently shown promising object detection results and attracted increasing attention. However, how to develop effective domain adaptation techniques to improve its cross-domain performance remains unexplored and unclear. In this paper, we delve into this topic and empirically find that direct feature distribution alignment on the CNN backbone only brings limited improvements, as it does not guarantee domain-invariant sequence features in the transformer for prediction. To address this issue, we propose a novel Sequence Feature Alignment (SFA) method that is specially designed for the adaptation of detection transformers. Technically, SFA consists of a domain query-based feature alignment (DQFA) module and a token-wise feature alignment (TFA) module. In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains. DQFA reduces the domain discrepancy in global feature representations and object relations when deploying in the transformer encoder and decoder, respectively. Meanwhile, TFA aligns token features in the sequence from both domains, which reduces the domain gaps in local and instance-level feature representations in the transformer encoder and decoder, respectively. Besides, a novel bipartite matching consistency loss is proposed to enhance the feature discriminability for robust object detection. Experiments on three challenging benchmarks show that SFA outperforms state-of-the-art domain adaptive object detection methods. Code has been made available at: https://github.com/encounter1997/SFA.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection

    Mar 19, 2026Haochen Li, Rui Zhang, Hantao Yao +5Object DetectionUnsupervised Domain Adaptation

  2. ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection

    Mar 12, 2026Mattia Bernardi, Chiara Cappellino, Matteo Mosconi +3Open-Vocabulary Object DetectionVision Foundation Model Adaptation

  3. CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection

    Feb 26, 2026Boyang Dai, Zeng Fan, Zihao Qi +2Object DetectionSource-Free Domain Adaptation