News

Pytorch official code of QEM is opened. (01/16/2020)
Pytorch official code of QANet is released. (01/11/2020)

Introduction

Official implementation of Quality Enhancement Network for Instance-Level Dense Prediction

In this repository, we release the QEM code in Pytorch.

QEM architecture:

Citing QANet & QEM

If you use QANet & QEM, please use the following BibTeX entry.

@inproceedings{yang2021qanet,
  title = {Quality-Aware Network for Human Parsing},
  author = {Lu Yang and Qing Song and Zhihui Wang and Zhiwei Liu and Songcen Xu and Zhihao Li},
  booktitle = {arXiv preprint arXiv:2103.05997},
  year = {2020}
}

@inproceedings{yang2021qem,
  title = {Quality-Aware Network for Instance-Level Dense Prediction},
  author = {Lu Yang and Qing Song and Zhihui Wang and Zhiwei Liu and Songcen Xu and Zhihao Li},
  booktitle = {arXiv preprint arXiv:21xx.xxxxx},
  year = {2021}
}

Installation

8 x TITAN RTX GPU
pytorch1.6
python3.6.8

Install QANet following INSTALL.md.

Data Prepare

Please follow DATA_PREPARE.md to download training and evaluating data.

Results and Models

QANet On CIHP

Backbone	mIoU	APp/APp50/PCP50	APr/APr50	DOWNLOAD
ResNet50	62.9	60.1/74.3/68.9	56.2/63.5	GoogleDrive
ResNet101	64.1	62.0/77.9/72.4	57.9/65.6
HRNet-W48	66.1	64.5/81.3/75.7	60.8/68.8	GoogleDrive

QANet On LIP

Backbone	Input Size	pixAcc.	meanAcc.	mIoU	DOWNLOAD
HRNet-W48	512×384	88.92	71.87	59.61	GoogleDrive
HRNet-W48	544×416	89.19	72.97	60.52	GoogleDrive

Flip test is used.
For CIHP, we use FCOS-R50 to detect person (73.1 AP on CIHP val).
Multi-scale test is used for LIP.

ImageNet pretrained weights

please put the pretrained weights in QANet/weights

Training

To train a model with 8 GPUs run:

python tools/train_net_all.py --cfg cfgs/CIHP/QANet/QANet_R-50c_512x384_1x.yaml

Evaluation

multi-gpu evaluation,

python tools/test_net_all.py --cfg ckpts/CIHP/QANet/QANet_R-50c_512x384_1x/QANet_R-50c_512x384_1x.yaml --gpu_id 0,1,2,3,4,5,6,7

single-gpu evaluation,

python tools/test_net_all.py --cfg ckpts/CIHP/QANet/QANet_R-50c_512x384_1x/QANet_R-50c_512x384_1x.yaml --gpu_id 0

License

QANet is released under the MIT license.

soeaver/QualityFormer