Progressive Domain Adaptation for Object Detection
Implementation of our paper Progressive Domain Adaptation for Object Detection, based on pytorch-faster-rcnn and PyTorch-CycleGAN.
Paper
Progressive Domain Adaptation for Object Detection Han-Kai Hsu, Chun-Han Yao, Yi-Hsuan Tsai, Wei-Chih Hung, Hung-Yu Tseng, Maneesh Singh and Ming-Hsuan Yang IEEE Winter Conference on Applications of Computer Vision (WACV), 2020.
Please cite our paper if you find it useful for your research.
@inproceedings{hsu2020progressivedet,
author = {Han-Kai Hsu and Chun-Han Yao and Yi-Hsuan Tsai and Wei-Chih Hung and Hung-Yu Tseng and Maneesh Singh and Ming-Hsuan Yang},
booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
title = {Progressive Domain Adaptation for Object Detection},
year = {2020}
}
Dependencies
This code is tested with Pytorch 0.4.1 and CUDA 9.0
# Pytorch via pip: Download and install Pytorch 0.4.1 wheel for CUDA 9.0
# from https://download.pytorch.org/whl/cu90/torch_stable.html
# Pytorch via conda:
conda install pytorch=0.4.1 cuda90 -c pytorch
# Other dependencies:
pip install -r requirements.txt
sh ./lib/make.sh
Data Preparation
KITTI
- Download the data from here.
- Extract the files under
data/KITTI/
Cityscapes
- Download the data from here.
- Extract the files under
data/CityScapes/
Foggy Cityscapes
- Follow the instructions here to request for the dataset download.
- Locate the data under
data/CityScapes/leftImg8bit/asfoggytrainandfoggyval.
BDD100k
- Download the data from here.
- Extract the files under
data/bdd100k/
Generate synthetic data with CycleGAN
Generate the synthetic data with the PyTorch-CycleGAN implementation.
git clone https://github.com/aitorzip/PyTorch-CycleGAN
Dataset loader code
Import the dataset loader code in ./cycleGAN_dataset_loader/ to train/test the CycleGAN on corresponding image translation task.
Generate from pre-trained weight:
Follow the testing instructions on PyTorch-CycleGAN and download the weight below to generate synthetic images. (Remember to change to the corresponding output image size)
- KITTI with Cityscapes style (KITTI->Cityscapes): size=(376,1244) Locate the generated data under
data/KITTI/training/synthCity_image_2/with same naming and folder structure as original KITTI data. - Cityscapes with FoggyCityscapes style (Cityscapes->FoggyCityscapes): size=(1024,2048) Locate the generated data under
data/CityScapes/leftImg8bit/synthFoggytrainwith same naming and folder structure as original Cityscapes data. - Cityscapes with BDD style (Cityscpaes->BDD100k): size=(1024,1280) Locate the generated data under
data/CityScapes/leftImg8bit/synthBDDdaytrainanddata/CityScapes/leftImg8bit/synthBDDdayvalwith same naming and folder structure as original Cityscapes data.
Train your own CycleGAN:
Please follow the training instructions on PyTorch-CycleGAN.
Test the adaptation model
Download the following adapted weights to ./trained_weights/adapt_weight/
./experiments/scripts/test_adapt_faster_rcnn_stage1.sh [GPU_ID] [Adapt_mode] vgg16
# Specify the GPU_ID you want to use
# Adapt_mode selection:
# 'K2C': KITTI->Cityscapes
# 'C2F': Cityscapes->Foggy Cityscapes
# 'C2BDD': Cityscapes->BDD100k_day
# Example:
./experiments/scripts/test_adapt_faster_rcnn_stage2.sh 0 K2C vgg16
Train your own model
Stage one
./experiments/scripts/train_adapt_faster_rcnn_stage1.sh [GPU_ID] [Adapt_mode] vgg16
# Specify the GPU_ID you want to use
# Adapt_mode selection:
# 'K2C': KITTI->Cityscapes
# 'C2F': Cityscapes->Foggy Cityscapes
# 'C2BDD': Cityscapes->BDD100k_day
# Example:
./experiments/scripts/train_adapt_faster_rcnn_stage1.sh 0 K2C vgg16
Download the following pretrained detector weights to ./trained_weights/pretrained_detector/
Stage two
./experiments/scripts/train_adapt_faster_rcnn_stage2.sh 0 K2C vgg16
Discriminator score files:
- netD_synthC_score.json
- netD_CsynthFoggyC_score.json
- netD_CsynthBDDday_score.json
Extract the pretrained CycleGAN discriminator scores to ./trained_weights/
or
Save a dictionary of CycleGAN discriminator scores with image name as key and score as value
Ex: {'jena_000074_000019_leftImg8bit.png': 0.64}
Detection results
Adaptation results
Acknowledgement
Thanks to the awesome implementations from pytorch-faster-rcnn and PyTorch-CycleGAN.
29 Nov 30, 2022
58 Nov 6, 2022
80 Dec 25, 2022
84 Dec 26, 2022
238 Dec 22, 2022
569 Dec 30, 2022
2 Oct 7, 2022
5 Dec 10, 2022
3 Jan 26, 2022
66 Dec 16, 2022
36 Dec 5, 2022
79 Dec 19, 2022
66 Dec 20, 2022
75 Dec 16, 2022
26 Dec 26, 2022
54 Dec 22, 2022
8 Apr 16, 2022
85 Dec 7, 2022
26 Sep 22, 2022