Bibliographic Details
| Title: |
RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer |
| Authors: |
Lv, Wenyu, Zhao, Yian, Chang, Qinyao, Huang, Kui, Wang, Guanzhong, Liu, Yi |
| Publication Year: |
2024 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Computer Vision and Pattern Recognition |
| More Details: |
In this report, we present RT-DETRv2, an improved Real-Time DEtection TRansformer (RT-DETR). RT-DETRv2 builds upon the previous state-of-the-art real-time detector, RT-DETR, and opens up a set of bag-of-freebies for flexibility and practicality, as well as optimizing the training strategy to achieve enhanced performance. To improve the flexibility, we suggest setting a distinct number of sampling points for features at different scales in the deformable attention to achieve selective multi-scale feature extraction by the decoder. To enhance practicality, we propose an optional discrete sampling operator to replace the grid_sample operator that is specific to RT-DETR compared to YOLOs. This removes the deployment constraints typically associated with DETRs. For the training strategy, we propose dynamic data augmentation and scale-adaptive hyperparameters customization to improve performance without loss of speed. Source code and pre-trained models will be available at https://github.com/lyuwenyu/RT-DETR. |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2407.17140 |
| Accession Number: |
edsarx.2407.17140 |
| Database: |
arXiv |
