FemtoDet

Official codes of ICCV2023 paper: <>

Dependencies

• Python 3.8
• Torch 1.9.1+cu111
• Torchvision 0.10.1+cu111
• mmcv-full 1.4.2
• mmdet 2.23.0

Installation

Do it as mmdetection had done.

Preparation

1. Download the dataset.

We mainly train FemtoDet on Pascal VOC 0712, you should firstly download the datasets. By default, we assume the dataset is stored in ./data/.

1. Dataset preparation.

Then, you can move all images to ./data/voc2coco/jpeg/;you can use our converted coco format annotation files(umbz) and put these files to ./data/voc2coco/annotations/; finally, the directory structure is

*data/voc2coco *jpeg *2008_003841.jpg *... *annotations *trainvoc_annotations.json *testvoc_annotations.json

1. Download the initialized models.

We trained our designed backbone on ImageNet 1k, and used it for the inite weights)(hx8k) of FemtoDet.

FemtoDet/weights/*

Training

bash ./tools/train_femtodet.sh 4

Results (trained on VOC) and Models

trained model and logs download (7aok) ```

| Detector | Params | box AP50 | Config |

| | | 37.1 | ./configs/femtoDet/femtodet0stage.py | ----------------------------------------------------- | FemtoDet | 68.77k | 40.4 | ./configs/femtoDet/femtodet1stage.py | ----------------------------------------------------- | | | 44.4 | ./configs/femtoDet/femtodet_2stage.py | -----------------------------------------------------

| | | 46.5 | ./configs/femtoDet/femtodet_3stage.py |

```

Links of Deployment (exploring to onnx) and FemtoDet in mmdet3 versions.

References

If you find the code useful for your research, please consider citing: bib @InProceedings{Tu_2023_ICCV, author = {Tu, Peng and Xie, Xu and Ai, Guo and Li, Yuexiang and Huang, Yawen and Zheng, Yefeng}, title = {FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13318-13327} } @misc{tu2023femtodet, title={FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs}, author={Peng Tu and Xu Xie and Guo AI and Yuexiang Li and Yawen Huang and Yefeng Zheng}, year={2023}, eprint={2301.06719}, archivePrefix={arXiv}, primaryClass={cs.CV} }