DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911678793252864 |
|---|---|
| author | Wang, Siheng Li, Yanshu Hu, Bohan Li, Zhengdao Zhan, Haibo Li, Linshan Liu, Weiming Qian, Ruizhi Wu, Guangxin Zhang, Hao Shen, Jifeng Koniusz, Piotr Yao, Zhengtao Dong, Junhao Sun, Qiang |
| author_facet | Wang, Siheng Li, Yanshu Hu, Bohan Li, Zhengdao Zhan, Haibo Li, Linshan Liu, Weiming Qian, Ruizhi Wu, Guangxin Zhang, Hao Shen, Jifeng Koniusz, Piotr Yao, Zhengtao Dong, Junhao Sun, Qiang |
| contents | Open-vocabulary object detection (OVOD) enables models to recognize objects beyond predefined categories, but existing approaches remain limited in practical deployment. On the one hand, multimodal designs often incur substantial computational overhead due to their reliance on text encoders at inference time. On the other hand, tightly coupled training objectives introduce a trade-off between closed-set detection accuracy and open-world generalization. Thus, we propose Decoupled Cognition DETR (DeCo-DETR), a vision-centric framework that addresses these challenges through a unified decoupling paradigm. Instead of depending on online text encoding, DeCo-DETR constructs a hierarchical semantic prototype space from region-level descriptions generated by pre-trained LVLMs and aligned via CLIP, enabling efficient and reusable semantic representation. Building upon this representation, the framework further disentangles semantic reasoning from localization through a decoupled training strategy, which separates alignment and detection into parallel optimization streams. Extensive experiments on standard OVOD benchmarks demonstrate that DeCo-DETR achieves competitive zero-shot detection performance while significantly improving inference efficiency. These results highlight the effectiveness of decoupling semantic cognition from detection, offering a practical direction for scalable OVOD systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02753 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection Wang, Siheng Li, Yanshu Hu, Bohan Li, Zhengdao Zhan, Haibo Li, Linshan Liu, Weiming Qian, Ruizhi Wu, Guangxin Zhang, Hao Shen, Jifeng Koniusz, Piotr Yao, Zhengtao Dong, Junhao Sun, Qiang Computer Vision and Pattern Recognition Open-vocabulary object detection (OVOD) enables models to recognize objects beyond predefined categories, but existing approaches remain limited in practical deployment. On the one hand, multimodal designs often incur substantial computational overhead due to their reliance on text encoders at inference time. On the other hand, tightly coupled training objectives introduce a trade-off between closed-set detection accuracy and open-world generalization. Thus, we propose Decoupled Cognition DETR (DeCo-DETR), a vision-centric framework that addresses these challenges through a unified decoupling paradigm. Instead of depending on online text encoding, DeCo-DETR constructs a hierarchical semantic prototype space from region-level descriptions generated by pre-trained LVLMs and aligned via CLIP, enabling efficient and reusable semantic representation. Building upon this representation, the framework further disentangles semantic reasoning from localization through a decoupled training strategy, which separates alignment and detection into parallel optimization streams. Extensive experiments on standard OVOD benchmarks demonstrate that DeCo-DETR achieves competitive zero-shot detection performance while significantly improving inference efficiency. These results highlight the effectiveness of decoupling semantic cognition from detection, offering a practical direction for scalable OVOD systems. |
| title | DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.02753 |