2anchao / DynamicHead

Dynamic Head: Unifying Object Detection Heads with Attentions

dyhead_video.mp4

This is the official implementation of CVPR 2021 paper "Dynamic Head: Unifying Object Detection Heads with Attentions".

"In this paper, we present a novel dynamic head framework to unify object detection heads with attentions. By coherently combining multiple self-attention mechanisms between feature levels for scale-awareness, among spatial locations for spatial-awareness, and within output channels for task-awareness, the proposed approach significantly improves the representation ability of object detection heads without any computational overhead."

Dynamic Head: Unifying Object Detection Heads With Attentions

Xiyang Dai, Yinpeng Chen, Bin Xiao, Dongdong Chen, Mengchen Liu, Lu Yuan, Lei Zhang

Model Zoo

Code and Model are under internal review and will release soon. Stay tuned!

In order to open-source, we have ported the implementation from our internal framework to Detectron2 and re-train the models.

We notice better performances on some models compared to original paper.

Config	Model	Backbone	Scheduler	COCO mAP	Weight
cfg	FasterRCNN + DyHead	R50	1x	40.3	weight
cfg	RetinaNet + DyHead	R50	1x	39.9	weight
cfg	ATSS + DyHead	R50	1x	42.4	weight
cfg	ATSS + DyHead	Swin-Tiny	2x + ms	49.8	weight

Usage

Dependencies:

Detectron2, timm

Installation:

python -m pip install -e DynamicHead

Train:

To train a config on a single node with 8 gpus, simply use:

DETECTRON2_DATASETS=$DATASET python train_net.py --config configs/dyhead_r50_retina_fpn_1x.yaml --num-gpus 8

Test:

To test a config with a weight on a single node with 8 gpus, simply use:

DETECTRON2_DATASETS=$DATASET python train_net.py --config configs/dyhead_r50_retina_fpn_1x.yaml --num-gpus 8 --eval-only MODEL.WEIGHTS $WEIGHT

Citation

@InProceedings{Dai_2021_CVPR,
    author    = {Dai, Xiyang and Chen, Yinpeng and Xiao, Bin and Chen, Dongdong and Liu, Mengchen and Yuan, Lu and Zhang, Lei},
    title     = {Dynamic Head: Unifying Object Detection Heads With Attentions},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {7373-7382}
}

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [e-mail] with any additional questions or comments.