This is a PyTorch implementation of 'Domain Adaptive Faster R-CNN for Object Detection in the Wild', implemented by Haoran Wang(haowang@student.ethz.ch). The original paper can be found here. This implementation is built on maskrcnn-benchmark @ e60f4ec.
If you find this repository useful, please cite the oringinal paper:
@inproceedings{chen2018domain,
title={Domain Adaptive Faster R-CNN for Object Detection in the Wild},
author = {Chen, Yuhua and Li, Wen and Sakaridis, Christos and Dai, Dengxin and Van Gool, Luc},
booktitle = {Computer Vision and Pattern Recognition (CVPR)},
year = {2018}
}
and maskrnn-benchmark:
@misc{massa2018mrcnn,
author = {Massa, Francisco and Girshick, Ross},
title = {{maskrnn-benchmark: Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch}},
year = {2018},
howpublished = {url{https://github.com/facebookresearch/maskrcnn-benchmark}},
note = {Accessed: [Insert date here]}
}
Installation
Please follow the instruction in maskrcnn-benchmark to install and use Domain-Adaptive-Faster-RCNN-PyTorch.
Example Usage
An example of Domain Adaptive Faster R-CNN with FPN adapting from Cityscapes dataset to Foggy Cityscapes dataset is provided:
Follow the example in Detectron-DA-Faster-RCNN to download dataset and generate coco style annoation files
Symlink the path to the Cityscapes and Foggy Cityscapes dataset to datasets/ as follows:
Pretrained model with image+instance+consistency domain adaptation on Resnet-50 bakcbone for Cityscapes->Foggy Cityscapes task is provided. For those who might be interested, the corresponding training log could be checked at here. The following results are all tested with Resnet-50 backbone.
image
instsnace
consistency
AP@50
Faster R-CNN
24.9
DA Faster R-CNN
✓
38.3
DA Faster R-CNN
✓
38.8
DA Faster R-CNN
✓
✓
40.8
DA Faster R-CNN
✓
✓
✓
41.0
Other Implementation
da-faster-rcnn based on Caffe. (original code by paper authors)