Home

Awesome

OneNet: What Makes for End-to-End Object Detection?

License: MIT

Comparisons of different label assignment methods. H and W are height and width of feature map, respectively, K is number of object categories. Previous works on one-stage object detection assign labels by only position cost, such as (a) box IoU or (b) point distance between sample and ground-truth. In our method, however, (c) classification cost is additionally introduced. We discover that classification cost is the key to the success of end-to-end. Without classification cost, only location cost leads to redundant boxes of high confidence scores in inference, making NMS post-processing a necessary component.

Introduction

arxiv: OneNet: Towards End-to-End One-Stage Object Detection

paper: What Makes for End-to-End Object Detection?

Updates

Comming

Models on COCO

We provide two models

Methodinf_timetrain_timebox APdownload
R18_dcn109 FPS20h29.9model | log
R18_nodcn138 FPS13h27.7model | log
R50_dcn67 FPS36h35.7model | log
R50_nodcn73 FPS29h32.7model | log
R50_RetinaNet26 FPS31h37.5model | log
R50_FCOS27 FPS21h38.9model | log

If download link is invalid, models and logs are also available in Github Release and Baidu Drive by code nhr8.

Notes

Models on CrowdHuman

Methodinf_timetrain_timeAP50mMRrecalldownload
R50_RetinaNet26 FPS11.5h90.948.898.0model | log
R50_FCOS27 FPS4.5h90.648.697.7model | log

If download link is invalid, models and logs are also available in Github Release and Baidu Drive by code nhr8.

Notes

Installation

The codebases are built on top of Detectron2 and DETR.

Requirements

Steps

  1. Install and build libs
git clone https://github.com/PeizeSun/OneNet.git
cd OneNet
python setup.py build develop
  1. Link coco dataset path to OneNet/datasets/coco
mkdir -p datasets/coco
ln -s /path_to_coco_dataset/annotations datasets/coco/annotations
ln -s /path_to_coco_dataset/train2017 datasets/coco/train2017
ln -s /path_to_coco_dataset/val2017 datasets/coco/val2017
  1. Train OneNet
python projects/OneNet/train_net.py --num-gpus 8 \
    --config-file projects/OneNet/configs/onenet.res50.dcn.yaml
  1. Evaluate OneNet
python projects/OneNet/train_net.py --num-gpus 8 \
    --config-file projects/OneNet/configs/onenet.res50.dcn.yaml \
    --eval-only MODEL.WEIGHTS path/to/model.pth
  1. Visualize OneNet
python demo/demo.py\
    --config-file projects/OneNet/configs/onenet.res50.dcn.yaml \
    --input path/to/images --output path/to/save_images --confidence-threshold 0.4 \
    --opts MODEL.WEIGHTS path/to/model.pth

License

OneNet is released under MIT License.

Citing

If you use OneNet in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:


@InProceedings{peize2020onenet,
  title = 	 {What Makes for End-to-End Object Detection?},
  author =       {Sun, Peize and Jiang, Yi and Xie, Enze and Shao, Wenqi and Yuan, Zehuan and Wang, Changhu and Luo, Ping},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {9934--9944},
  year = 	 {2021},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  publisher =    {PMLR},
}