LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911906317467648 |
|---|---|
| author | Chen, Qiang Su, Xiangbo Zhang, Xinyu Wang, Jian Chen, Jiahui Shen, Yunpeng Han, Chuchu Chen, Ziliang Xu, Weixiang Li, Fanrong Zhang, Shan Yao, Kun Ding, Errui Zhang, Gang Wang, Jingdong |
| author_facet | Chen, Qiang Su, Xiangbo Zhang, Xinyu Wang, Jian Chen, Jiahui Shen, Yunpeng Han, Chuchu Chen, Ziliang Xu, Weixiang Li, Fanrong Zhang, Shan Yao, Kun Ding, Errui Zhang, Gang Wang, Jingdong |
| contents | In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages recent advanced techniques, such as training-effective techniques, e.g., improved loss and pretraining, and interleaved window and global attentions for reducing the ViT encoder complexity. We improve the ViT encoder by aggregating multi-level feature maps, and the intermediate and final feature maps in the ViT encoder, forming richer feature maps, and introduce window-major feature map organization for improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time detectors, e.g., YOLO and its variants, on COCO and other benchmark datasets. Code and models are available at (https://github.com/Atten4Vis/LW-DETR). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03459 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection Chen, Qiang Su, Xiangbo Zhang, Xinyu Wang, Jian Chen, Jiahui Shen, Yunpeng Han, Chuchu Chen, Ziliang Xu, Weixiang Li, Fanrong Zhang, Shan Yao, Kun Ding, Errui Zhang, Gang Wang, Jingdong Computer Vision and Pattern Recognition In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages recent advanced techniques, such as training-effective techniques, e.g., improved loss and pretraining, and interleaved window and global attentions for reducing the ViT encoder complexity. We improve the ViT encoder by aggregating multi-level feature maps, and the intermediate and final feature maps in the ViT encoder, forming richer feature maps, and introduce window-major feature map organization for improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time detectors, e.g., YOLO and its variants, on COCO and other benchmark datasets. Code and models are available at (https://github.com/Atten4Vis/LW-DETR). |
| title | LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.03459 |