Unsupervised Domain Adaptation for Remote Sensing Vehicle Detection using Domain-specific Channel Recalibration
A Pytorch Implementation of Unsupervised Domain Adaptation for Remote Sensing Vehicle Detection using Domain-specific Channel Recalibration.
Please follow DA_Detection respository to setup the environment. In this project, we use Pytorch 0.4.0.
- GTAV10k dataset: Download our GTAV10k dataset, see dataset preparation code in DA-Faster RCNN.
All codes are written to fit for the format of PASCAL_VOC.
If you want to use this code on your own dataset, please arrange the dataset in the format of PASCAL, make dataset class in lib/datasets/, and add it to lib/datasets/factory.py, lib/datasets/config_dataset.py. Then, add the dataset option to lib/model/utils/parser_func.py.
In our experiments, we used two pre-trained models on ImageNet, i.e., VGG16 and ResNet101. Please download these two models from:
Download them and write the path in __C.VGG_PATH and __C.RESNET_PATH at lib/model/utils/config.py.
CUDA_VISIBLE_DEVICES=$GPU_ID \
python trainval_DSCR_DWPA.py --gc --cuda --lr 0.001 --net res101 --dataset gta_car --dataset_t ucas_car --save_dir path_to_save
CUDA_VISIBLE_DEVICES=$GPU_ID \
python test_DSCR_DWPA.py --gc --dataset ucas_car --net res101 --cuda --load_name path_to_model