DQ-DETR: DETR with Dynamic Query for Tiny Object Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913569246806016 |
|---|---|
| author | Huang, Yi-Xin Liu, Hou-I Shuai, Hong-Han Cheng, Wen-Huang |
| author_facet | Huang, Yi-Xin Liu, Hou-I Shuai, Hong-Han Cheng, Wen-Huang |
| contents | Despite previous DETR-like methods having performed successfully in generic object detection, tiny object detection is still a challenging task for them since the positional information of object queries is not customized for detecting tiny objects, whose scale is extraordinarily smaller than general objects. Also, DETR-like methods using a fixed number of queries make them unsuitable for aerial datasets, which only contain tiny objects, and the numbers of instances are imbalanced between different images. Thus, we present a simple yet effective model, named DQ-DETR, which consists of three different components: categorical counting module, counting-guided feature enhancement, and dynamic query selection to solve the above-mentioned problems. DQ-DETR uses the prediction and density maps from the categorical counting module to dynamically adjust the number of object queries and improve the positional information of queries. Our model DQ-DETR outperforms previous CNN-based and DETR-like methods, achieving state-of-the-art mAP 30.2% on the AI-TOD-V2 dataset, which mostly consists of tiny objects. Our code will be available at https://github.com/hoiliu-0801/DQ-DETR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03507 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DQ-DETR: DETR with Dynamic Query for Tiny Object Detection Huang, Yi-Xin Liu, Hou-I Shuai, Hong-Han Cheng, Wen-Huang Computer Vision and Pattern Recognition Despite previous DETR-like methods having performed successfully in generic object detection, tiny object detection is still a challenging task for them since the positional information of object queries is not customized for detecting tiny objects, whose scale is extraordinarily smaller than general objects. Also, DETR-like methods using a fixed number of queries make them unsuitable for aerial datasets, which only contain tiny objects, and the numbers of instances are imbalanced between different images. Thus, we present a simple yet effective model, named DQ-DETR, which consists of three different components: categorical counting module, counting-guided feature enhancement, and dynamic query selection to solve the above-mentioned problems. DQ-DETR uses the prediction and density maps from the categorical counting module to dynamically adjust the number of object queries and improve the positional information of queries. Our model DQ-DETR outperforms previous CNN-based and DETR-like methods, achieving state-of-the-art mAP 30.2% on the AI-TOD-V2 dataset, which mostly consists of tiny objects. Our code will be available at https://github.com/hoiliu-0801/DQ-DETR. |
| title | DQ-DETR: DETR with Dynamic Query for Tiny Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.03507 |