MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929739572183040 |
|---|---|
| author | Nan, Zhixiong Li, Xianghong Dai, Jifeng Xiang, Tao |
| author_facet | Nan, Zhixiong Li, Xianghong Dai, Jifeng Xiang, Tao |
| contents | Based on analyzing the character of cascaded decoder architecture commonly adopted in existing DETR-like models, this paper proposes a new decoder architecture. The cascaded decoder architecture constrains object queries to update in the cascaded direction, only enabling object queries to learn relatively-limited information from image features. However, the challenges for object detection in natural scenes (e.g., extremely-small, heavily-occluded, and confusingly mixed with the background) require an object detection model to fully utilize image features, which motivates us to propose a new decoder architecture with the parallel Multi-time Inquiries (MI) mechanism. MI enables object queries to learn more comprehensive information, and our MI based model, MI-DETR, outperforms all existing DETR-like models on COCO benchmark under different backbones and training epochs, achieving +2.3 AP and +0.6 AP improvements compared to the most representative model DINO and SOTA model Relation-DETR under ResNet-50 backbone. In addition, a series of diagnostic and visualization experiments demonstrate the effectiveness, rationality, and interpretability of MI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01463 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism Nan, Zhixiong Li, Xianghong Dai, Jifeng Xiang, Tao Computer Vision and Pattern Recognition Based on analyzing the character of cascaded decoder architecture commonly adopted in existing DETR-like models, this paper proposes a new decoder architecture. The cascaded decoder architecture constrains object queries to update in the cascaded direction, only enabling object queries to learn relatively-limited information from image features. However, the challenges for object detection in natural scenes (e.g., extremely-small, heavily-occluded, and confusingly mixed with the background) require an object detection model to fully utilize image features, which motivates us to propose a new decoder architecture with the parallel Multi-time Inquiries (MI) mechanism. MI enables object queries to learn more comprehensive information, and our MI based model, MI-DETR, outperforms all existing DETR-like models on COCO benchmark under different backbones and training epochs, achieving +2.3 AP and +0.6 AP improvements compared to the most representative model DINO and SOTA model Relation-DETR under ResNet-50 backbone. In addition, a series of diagnostic and visualization experiments demonstrate the effectiveness, rationality, and interpretability of MI. |
| title | MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.01463 |