Scale-aware Automatic Augmentation for Object Detection

Yukang Chen, Yanwei Li, Tao Kong, Lu Qi, Ruihang Chu, Lei Li, Jiaya Jia

[Paper] [BibTeX]

This project provides the implementation for the CVPR 2021 paper "Scale-aware Automatic Augmentation for Object Detection". Scale-aware AutoAug provides a new search space and search metric to find effective data agumentation policies for object detection. It is implemented on maskrcnn-benchmark and FCOS. Both search and training codes have been released. To facilitate more use, we re-implement the training code based on Detectron2.

For maskrcnn-benchmark code, please follow INSTALL.md for instruction.

For FCOS code, please follow INSTALL.md for instruction.

For Detectron2 code, please follow INSTALL.md for instruction.

(You can skip this step and directly train on our searched policies.)

To search with 8 GPUs, run:

cd /path/to/SA-AutoAug/maskrcnn-benchmark
export NGPUS=8
python3 -m torch.distributed.launch --nproc_per_node=$NGPUS tools/search.py --config-file configs/SA_AutoAug/retinanet_R-50-FPN_search.yaml OURPUT_DIR /path/to/searchlog_dir

Since we finetune on an existing baseline model during search, a baseline model is needed. You can download this model for search, or you can use other Retinanet baseline model trained by yourself.

To train the searched policies on maskrcnn-benchmark (FCOS)

cd /path/to/SA-AutoAug/maskrcnn-benchmark
export NGPUS=8
python3 -m torch.distributed.launch --nproc_per_node=$NGPUS tools/train_net.py --config-file configs/SA_AutoAug/CONFIG_FILE  OUTPUT_DIR /path/to/traininglog_dir

For example, to train the retinanet ResNet-50 model with our searched data augmentation policies in 6x schedule:

cd /path/to/SA-AutoAug/maskrcnn-benchmark
export NGPUS=8
python3 -m torch.distributed.launch --nproc_per_node=$NGPUS tools/train_net.py --config-file configs/SA_AutoAug/retinanet_R-50-FPN_6x.yaml  OUTPUT_DIR models/retinanet_R-50-FPN_6x_SAAutoAug

To train the searched policies on detectron2

cd /path/to/SA-AutoAug/detectron2
python3 ./tools/train_net.py --num-gpus 8 --config-file ./configs/COCO-Detection/SA_AutoAug/CONFIG_FILE OUTPUT_DIR /path/to/traininglog_dir

For example, to train the retinanet ResNet-50 model with our searched data augmentation policies in 6x schedule:

cd /path/to/SA-AutoAug/detectron2
python3 ./tools/train_net.py --num-gpus 8 --config-file ./configs/COCO-Detection/SA_AutoAug/retinanet_R_50_FPN_6x.yaml OUTPUT_DIR output_retinanet_R_50_FPN_6x_SAAutoAug

We provide the results on COCO val2017 set with pretrained models.

Consider cite SA-Autoaug in your publications if it helps your research.

@inproceedings{saautoaug,
  title={Scale-aware Automatic Augmentation for Object Detection},
  author={Yukang Chen, Yanwei Li, Tao Kong, Lu Qi, Ruihang Chu, Lei Li, Jiaya Jia},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021}
}

This training code of this project is built on maskrcnn-benchmark, Detectron2, FCOS, and ATSS. The search code of this project is modified from DetNAS. Some augmentation code and settings follow AutoAug-Det. We thanks a lot for the authors of these projects.

Note that:

(1) We also provides script files for search and training in maskrcnn-benchmark, FCOS, and, detectron2.

(2) Any issues or pull requests on this project are welcome. In addition, if you meet problems when applying the augmentations to other datasets or codebase, feel free to contact Yukang Chen ([email protected]).