Architecture | ResNet, TridentNet Block, Soft-NMS |
---|---|
lr sched | 3X |
SHOW MORE |
Architecture | ResNet, TridentNet Block, Soft-NMS |
---|---|
lr sched | 1X |
SHOW MORE |
Architecture | ResNet, TridentNet Block, Soft-NMS, TridentNet |
---|---|
lr sched | 3X |
SHOW MORE |
TridentNet is an object detection architecture that aims to generate scale-specific feature maps with a uniform representational power. A parallel multi-branch architecture is constructed in which each branch shares the same transformation parameters but with different receptive fields. A scale-aware training scheme is used to specialize each branch by sampling object instances of proper scales for 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
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
@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}
}
MODEL | BOX AP | AP50 | AP75 | APS | APM | APL |
---|---|---|---|---|---|---|
TridentNet (R101-C4, C5-128ROI, 3X) | 43.6 | 63.4 | 47.0 | 24.3 | 47.8 | 60.0 |
Faster R-CNN (R101-C4, C5-512ROI, 3X) | 41.1 | 61.4 | 44.0 | 22.2 | 45.5 | 55.9 |
TridentNet (R50-C4, C5-128ROI, 3X) | 40.6 | 60.8 | 43.6 | 23.4 | 44.7 | 57.1 |
Faster R-CNN (R50-C4, C5-512ROI, 3X) | 38.4 | 58.7 | 41.3 | 20.7 | 42.7 | 53.1 |
TridentNet (R50-C4, C5-128ROI, 1X) | 38.0 | 58.1 | 40.8 | 19.5 | 42.2 | 54.6 |
Faster R-CNN (R50-C4, C5-512ROI, 1X) | 35.7 | 56.1 | 38.0 | 19.2 | 40.9 | 48.7 |