Home

Awesome

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection.

Paper Link: arxiv | CVPR 2023

<p align="center"> <img src="./images/framework.png" width="80%"> </p>

Dependencies

Dataset Preparation

# the dataset directory:
|-- ${image_dir}
   |-- WFLW
      | -- WFLW_images
   |-- 300W
      | -- afw
      | -- helen
      | -- ibug
      | -- lfpw
   |-- COFW
      | -- train
      | -- test
|-- ${annot_dir}
   |-- WFLW
      |-- train.tsv, test.tsv
   |-- 300W
      |-- train.tsv, test.tsv
   |--COFW
      |-- train.tsv, test.tsv

Usage

DatasetModel
WFLWgoogle / baidu
300Wgoogle / baidu
COFWgoogle / baidu

Training

python main.py --mode=train --device_ids=0,1,2,3 \
               --image_dir=${image_dir} --annot_dir=${annot_dir} \
               --data_definition={WFLW, 300W, COFW}

Testing

python main.py --mode=test --device_ids=0 \
               --image_dir=${image_dir} --annot_dir=${annot_dir} \
               --data_definition={WFLW, 300W, COFW} \
               --pretrained_weight=${model_path} \

Evaluation

python evaluate.py --device_ids=0 \
                   --model_path=${model_path} --metadata_path=${metadata_path} \
                   --image_dir=${image_dir} --data_definition={WFLW, 300W, COFW} \ 

To test on your own image, the following code could be considered:

python demo.py

Results

The models trained by STAR Loss achieved SOTA performance in all of COFW, 300W and WFLW datasets.

<p align="center"> <img src="./images/results.png" width="80%"> </p>

BibTeX Citation

Please consider citing our papers in your publications if the project helps your research. BibTeX reference is as follows.

@inproceedings{Zhou_2023_CVPR,
    author    = {Zhou, Zhenglin and Li, Huaxia and Liu, Hong and Wang, Nanyang and Yu, Gang and Ji, Rongrong},
    title     = {STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {15475-15484}
}

Acknowledgments

This repository is built on top of ADNet. Thanks for this strong baseline.