A newer version of the Streamlit SDK is available:
1.36.0
TridentNet in Detectron2
Scale-Aware Trident Networks for Object Detection
Yanghao Li*, Yuntao Chen*, Naiyan Wang, Zhaoxiang Zhang
[TridentNet] [arXiv] [BibTeX]
In this repository, we implement TridentNet-Fast in Detectron2. Trident Network (TridentNet) aims to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. TridentNet-Fast is a fast approximation version of TridentNet that could achieve significant improvements without any additional parameters and computational cost.
Training
To train a model, run
python /path/to/detectron2/projects/TridentNet/train_net.py --config-file <config.yaml>
For example, to launch end-to-end TridentNet training with ResNet-50 backbone on 8 GPUs, one should execute:
python /path/to/detectron2/projects/TridentNet/train_net.py --config-file configs/tridentnet_fast_R_50_C4_1x.yaml --num-gpus 8
Evaluation
Model evaluation can be done similarly:
python /path/to/detectron2/projects/TridentNet/train_net.py --config-file configs/tridentnet_fast_R_50_C4_1x.yaml --eval-only MODEL.WEIGHTS model.pth
Results on MS-COCO in Detectron2
| Model | Backbone | Head | lr sched | AP | AP50 | AP75 | APs | APm | APl | download |
|---|---|---|---|---|---|---|---|---|---|---|
| Faster | R50-C4 | C5-512ROI | 1X | 35.7 | 56.1 | 38.0 | 19.2 | 40.9 | 48.7 | model | metrics |
| TridentFast | R50-C4 | C5-128ROI | 1X | 38.0 | 58.1 | 40.8 | 19.5 | 42.2 | 54.6 | model | metrics |
| Faster | R50-C4 | C5-512ROI | 3X | 38.4 | 58.7 | 41.3 | 20.7 | 42.7 | 53.1 | model | metrics |
| TridentFast | R50-C4 | C5-128ROI | 3X | 40.6 | 60.8 | 43.6 | 23.4 | 44.7 | 57.1 | model | metrics |
| Faster | R101-C4 | C5-512ROI | 3X | 41.1 | 61.4 | 44.0 | 22.2 | 45.5 | 55.9 | model | metrics |
| TridentFast | R101-C4 | C5-128ROI | 3X | 43.6 | 63.4 | 47.0 | 24.3 | 47.8 | 60.0 | model | metrics |
Citing TridentNet
If you use TridentNet, please use the following BibTeX entry.
@InProceedings{li2019scale,
title={Scale-Aware Trident Networks for Object Detection},
author={Li, Yanghao and Chen, Yuntao and Wang, Naiyan and Zhang, Zhaoxiang},
journal={The International Conference on Computer Vision (ICCV)},
year={2019}
}