# Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework

arXiv: https://arxiv.org/abs/2310.15646 · HTML: https://mlsanity.com/paper/2310.15646/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 52 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 30 of 39)

- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (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)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [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)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [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)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [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)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [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)
- [Harmonizing Transferability and Discriminability for Adapting Object Detectors](https://mlsanity.com/paper/2003.06297/) (2020)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers](https://mlsanity.com/paper/2107.12636/) (2021)
- [Cross Domain Object Detection by Target-Perceived Dual Branch Distillation](https://mlsanity.com/paper/2205.01291/) (2022)
- [Why ResNet Works? Residuals Generalize](https://mlsanity.com/paper/1904.01367/) (2019)

## Built on by (most cited first, 13 of 13)

- [DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment](https://mlsanity.com/paper/2405.11765/) (2024)
- [Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection](https://mlsanity.com/paper/2407.16497/) (2024)
- [Source-Free Object Detection with Detection Transformer](https://mlsanity.com/paper/2510.11090/) (2025)
- [Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability](https://mlsanity.com/paper/2506.21042/) (2025)
- [Beyond Boundaries: Leveraging Vision Foundation Models for Source-Free Object Detection](https://mlsanity.com/paper/2511.07301/) (2025)
- [Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection](https://mlsanity.com/paper/2512.17514/) (2025)
- [Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher](https://mlsanity.com/paper/2407.07780/) (2024)
- [Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization](https://mlsanity.com/paper/2606.31373/) (2026)
- [RT-DATR: Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Alignment](https://mlsanity.com/paper/2504.09196/) (2025)
- [Domain Adaptive SAR Wake Detection: Leveraging Similarity Filtering and Memory Guidance](https://mlsanity.com/paper/2509.12279/) (2025)
- [Towards Unbiased Source-Free Object Detection via Vision Foundation Models](https://mlsanity.com/paper/2601.12765/) (2026)
- [DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection](https://mlsanity.com/paper/2603.18757/) (2026)
- [Real-Time Source-Free Object Detection](https://mlsanity.com/paper/2606.31834/) (2026)

## Abstract (arXiv)

Unsupervised domain adaptation object detection (UDAOD) research on Detection Transformer(DETR) mainly focuses on feature alignment and existing methods can be divided into two kinds, each of which has its unresolved issues. One-stage feature alignment methods can easily lead to performance fluctuation and training stagnation. Two-stage feature alignment method based on mean teacher comprises a pretraining stage followed by a self-training stage, each facing problems in obtaining reliable pretrained model and achieving consistent performance gains. Methods mentioned above have not yet explore how to utilize the third related domain such as target-like domain to assist adaptation. To address these issues, we propose a two-stage framework named MTM, i.e. Mean Teacher-DETR with Masked Feature Alignment. In the pretraining stage, we utilize labeled target-like images produced by image style transfer to avoid performance fluctuation. In the self-training stage, we leverage unlabeled target images by pseudo labels based on mean teacher and propose a module called Object Queries Knowledge Transfer (OQKT) to ensure consistent performance gains of the student model. Most importantly, we propose masked feature alignment methods including Masked Domain Query-based Feature Alignment (MDQFA) and Masked Token-wise Feature Alignment (MTWFA) to alleviate domain shift in a more robust way, which not only prevent training stagnation and lead to a robust pretrained model in the pretraining stage, but also enhance the model's target performance in the self-training stage. Experiments on three challenging scenarios and a theoretical analysis verify the effectiveness of MTM.