RT-DATR: Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Alignment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918168541265920 |
|---|---|
| author | Lv, Feng Li, Guoqing Li, Jin Xia, Chunlong |
| author_facet | Lv, Feng Li, Guoqing Li, Jin Xia, Chunlong |
| contents | Despite domain-adaptive object detectors based on CNN and transformers have made significant progress in cross-domain detection tasks, it is regrettable that domain adaptation for real-time transformer-based detectors has not yet been explored. Directly applying existing domain adaptation algorithms has proven to be suboptimal. In this paper, we propose RT-DATR, a simple and efficient real-time domain adaptive detection transformer. Building on RT-DETR as our base detector, we first introduce a local object-level feature alignment module to significantly enhance the feature representation of domain invariance during object transfer. Additionally, we introduce a scene semantic feature alignment module designed to boost cross-domain detection performance by aligning scene semantic features. Finally, we introduced a domain query and decoupled it from the object query to further align the instance feature distribution within the decoder layer, reduce the domain gap, and maintain discriminative ability. Experimental results on various cross-domian benchmarks demonstrate that our method outperforms current state-of-the-art approaches. Code is available at https://github.com/Jeremy-lf/RT-DATR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09196 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RT-DATR: Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Alignment Lv, Feng Li, Guoqing Li, Jin Xia, Chunlong Computer Vision and Pattern Recognition Despite domain-adaptive object detectors based on CNN and transformers have made significant progress in cross-domain detection tasks, it is regrettable that domain adaptation for real-time transformer-based detectors has not yet been explored. Directly applying existing domain adaptation algorithms has proven to be suboptimal. In this paper, we propose RT-DATR, a simple and efficient real-time domain adaptive detection transformer. Building on RT-DETR as our base detector, we first introduce a local object-level feature alignment module to significantly enhance the feature representation of domain invariance during object transfer. Additionally, we introduce a scene semantic feature alignment module designed to boost cross-domain detection performance by aligning scene semantic features. Finally, we introduced a domain query and decoupled it from the object query to further align the instance feature distribution within the decoder layer, reduce the domain gap, and maintain discriminative ability. Experimental results on various cross-domian benchmarks demonstrate that our method outperforms current state-of-the-art approaches. Code is available at https://github.com/Jeremy-lf/RT-DATR. |
| title | RT-DATR: Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Alignment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.09196 |