Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5912-5920
DOI: 10.1609/aaai.v38i6.28405 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Weixi Weng und 1 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Weng, W., & Yuan, C. (2024). Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5912-5920. https://doi.org/10.1609/aaai.v38i6.28405
Vancouver
Weng W, Yuan C. Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5912-5920. doi:10.1609/aaai.v38i6.28405
BibTeX
@article{Weng2024,
author = {Weng, Weixi and Yuan, Chun},
title = {Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {5912--5920},
doi = {10.1609/aaai.v38i6.28405}
}
EUVIMED