LPLD (Low-confidence Pseudo Label Distillation) (ECCV 2024)

This is an official code implementation repository for Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation, accepted to ECCV 2024.

---

Installation and Environmental settings (Instructions)

• We use Python 3.6 and Pytorch 1.9.0
• The codebase from Detectron2.

git clone https://github.com/junia3/LPLD.git

conda create -n LPLD python=3.6
conda activate LPLD
conda install pytorch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 cudatoolkit=10.2 -c pytorch

cd LPLD
pip install -r requirements.txt

## Make sure you have GCC and G++ version <=8.0
cd ..
python -m pip install -e LPLD

---

Dataset preparation

• Cityscapes, FoggyCityscapes / Download Webpage / Google drive (preprocessed)
• PASCAL_VOC / Download Webpage
• Clipart / Download Webpage / Google drive (preprocessed)
• Watercolor / Download Webpage / Google drive (preprocessed)
• Sim10k / Download Webpage

Make sure that all downloaded datasets are located in the ./dataset folder. After preparing the datasets, you will have the following file structure:

LPLD
...
├── dataset
│   └── foggy
│   └── cityscape
│   └── clipart
│   └── watercolor
...

Make sure that all dataset fit the format of PASCAL_VOC. For example, the dataset foggy is stored as follows:

$ cd ./dataset/foggy/VOC2007/
$ ls
Annotations  ImageSets  JPEGImages
$ cat ImageSets/Main/test_t.txt
target_munster_000157_000019_leftImg8bit_foggy_beta_0.02
target_munster_000124_000019_leftImg8bit_foggy_beta_0.02
target_munster_000110_000019_leftImg8bit_foggy_beta_0.02
.
.

---

Execution

Test models

CUDA_VISIBLE_DEVICES=$GPU_ID python tools/test_main.py --eval-only \ 
--config-file configs/sfda/sfda_city2foggy.yaml --model-dir $WEIGHT_LOCATION

---

Visualize

We provide visualization code. We use our trained model to detect foggy cityscapes in the example image.

---

Pretrained weights (LPLD)

Source	Target	Download Link
Cityscapes	FoggyCityscapes	Google drive
Kitti	Cityscapes	Google drive
Sim10k	Cityscapes	Google drive
Pascal VOC	Watercolor	Google drive
Pascal VOC	Clipart	Google drive

---

Citation

@article{yoon2024enhancing,
  title={Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation},
  author={Yoon, Ilhoon and Kwon, Hyeongjun and Kim, Jin and Park, Junyoung and Jang, Hyunsung and Sohn, Kwanghoon},
  journal={arXiv preprint arXiv:2407.13524},
  year={2024}
}