Transformed Dynamic Feature Pyramid for Small Object Detection
| Autor: | Jie Ren, Qiyao Liang, Hong Liang, Ying Yang, Qian Zhang, Linxia Feng |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Local and global context information
General Computer Science Computer science business.industry transformer module Feature extraction General Engineering Context (language use) Pattern recognition Object detection TK1-9971 transformed feature pyramid Transformation (function) single-scale transformation cross-scale transformation Feature (computer vision) General Materials Science Electrical engineering. Electronics. Nuclear engineering Pyramid (image processing) Artificial intelligence business Transformer (machine learning model) Block (data storage) |
| Zdroj: | IEEE Access, Vol 9, Pp 134649-134659 (2021) |
| ISSN: | 2169-3536 |
| DOI: | 10.1109/access.2021.3116324 |
| Popis: | The low resolution and less feature information of small targets make it difficult to recognize and locate, which greatly hinders the improvement of object detection accuracy. In this paper, an object detection model (TDFP) based on CNN and transformer was established, which combines local and global context to establish the connection between features. In the proposed transformed dynamic feature pyramid network, a transformer module was designed to dynamically transform and fuse the multi-scale features generated by the backbone to generate a transformed feature pyramid with richer multi-scale features and context information. In this transformation process, gate block is used to dynamically select single-scale transformation or cross-scale transformation to achieve an optimal style of transformation and fusion of multi-scale features. The experimental results show that the model improves the small targets detection accuracy based on CNN and transformer. Based on the backbone ResNeXt-101, TDFP achieves 46.2% AP and 26.3% APS on MS COCO, and takes the amount of computation as a loss constraint to achieve a better balance between detection accuracy and computational complexity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|