# Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

arXiv: https://arxiv.org/abs/2107.12636 · HTML: https://mlsanity.com/paper/2107.12636/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 54 references that are in the map.
- First posted on arXiv 27 Jul 2021.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Spectrally-normalized margin bounds for neural networks](https://mlsanity.com/paper/1706.08498/) (2017)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/1910.13049/) (2019)
- [Learning to Assemble Neural Module Tree Networks for Visual Grounding](https://mlsanity.com/paper/1812.03299/) (2018)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)
- [Multi-adversarial Faster-RCNN for Unrestricted Object Detection](https://mlsanity.com/paper/1907.10343/) (2019)
- [Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things](https://mlsanity.com/paper/2011.08612/) (2020)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [Object Relational Graph with Teacher-Recommended Learning for Video Captioning](https://mlsanity.com/paper/2002.11566/) (2020)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)
- [Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection](https://mlsanity.com/paper/1909.00597/) (2019)
- [Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition](https://mlsanity.com/paper/2105.06804/) (2021)
- [Group-aware Label Transfer for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2103.12366/) (2021)

## Built on by (most cited first, 30 of 49)

- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [An Empirical Study of Remote Sensing Pretraining](https://mlsanity.com/paper/2204.02825/) (2022)
- [Cross Domain Object Detection by Target-Perceived Dual Branch Distillation](https://mlsanity.com/paper/2205.01291/) (2022)
- [BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation](https://mlsanity.com/paper/2204.02811/) (2022)
- [Hierarchical Local-Global Transformer for Temporal Sentence Grounding](https://mlsanity.com/paper/2208.14882/) (2022)
- [MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer](https://mlsanity.com/paper/2205.01643/) (2022)
- [Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification](https://mlsanity.com/paper/2108.00139/) (2021)
- [Improving Transferability for Domain Adaptive Detection Transformers](https://mlsanity.com/paper/2204.14195/) (2022)
- [Exploiting Low-confidence Pseudo-labels for Source-free Object Detection](https://mlsanity.com/paper/2310.12705/) (2023)
- [Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework](https://mlsanity.com/paper/2310.15646/) (2023)
- [DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment](https://mlsanity.com/paper/2405.11765/) (2024)
- [DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification](https://mlsanity.com/paper/2304.09915/) (2023)
- [Align and Distill: Unifying and Improving Domain Adaptive Object Detection](https://mlsanity.com/paper/2403.12029/) (2024)
- [Learning to Purification for Unsupervised Person Re-identification](https://mlsanity.com/paper/2204.09931/) (2022)
- [Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection](https://mlsanity.com/paper/2407.16497/) (2024)
- [Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer](https://mlsanity.com/paper/2208.12527/) (2022)
- [VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions](https://mlsanity.com/paper/2211.12256/) (2022)
- [A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap](https://mlsanity.com/paper/2407.21438/) (2024)
- [BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection](https://mlsanity.com/paper/2211.17126/) (2022)
- [DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection](https://mlsanity.com/paper/2304.07082/) (2023)
- [DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception](https://mlsanity.com/paper/2401.08687/) (2024)
- [Differential Alignment for Domain Adaptive Object Detection](https://mlsanity.com/paper/2412.12830/) (2024)
- [BlenDA: Domain Adaptive Object Detection through diffusion-based blending](https://mlsanity.com/paper/2401.09921/) (2024)
- [D-MASTER: Mask Annealed Transformer for Unsupervised Domain Adaptation in Breast Cancer Detection from Mammograms](https://mlsanity.com/paper/2407.06585/) (2024)
- [Source-Free Object Detection with Detection Transformer](https://mlsanity.com/paper/2510.11090/) (2025)
- [Enhancing cross-domain detection: adaptive class-aware contrastive transformer](https://mlsanity.com/paper/2401.13264/) (2024)
- [Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection](https://mlsanity.com/paper/2504.20498/) (2025)
- [Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment](https://mlsanity.com/paper/2206.00222/) (2022)
- [PM-DETR: Domain Adaptive Prompt Memory for Object Detection with Transformers](https://mlsanity.com/paper/2307.00313/) (2023)
- [Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding](https://mlsanity.com/paper/2410.23570/) (2024)

## Abstract (arXiv)

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 (TDA) 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, TDA 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.