data
|__ ADEChallenge
    |__ ADEChallengeData2016
        |__ images
            |__ training
            |__ validation
        |__ annotations
            |__ training
            |__ validation

|__ CityScapes
    |__ leftImg8bit
        |__ train
        |__ val
        |__ test
    |__ gtFine
        |__ train
        |__ val
        |__ test

|__ CamVid
    |__ train
    |__ val
    |__ test
    |__ train_labels
    |__ val_labels
    |__ test_labels
    
|__ VOCdevkit
    |__ VOC2010
        |__ JPEGImages
        |__ SegmentationClassContext
        |__ ImageSets
            |__ SegmentationContext
                |__ train.txt
                |__ val.txt
    
|__ COCO
    |__ images
        |__ train2017
        |__ val2017
    |__ labels
        |__ train2017
        |__ val2017

|__ MHPv1
    |__ images
    |__ annotations
    |__ train_list.txt
    |__ test_list.txt

|__ MHPv2
    |__ train
        |__ images
        |__ parsing_annos
    |__ val
        |__ images
        |__ parsing_annos

|__ LIP
    |__ LIP
        |__ TrainVal_images
            |__ train_images
            |__ val_images
        |__ TrainVal_parsing_annotations
            |__ train_segmentations
            |__ val_segmentations

    |__ CIHP/CCIHP
        |__ instance-leve_human_parsing
            |__ Training
                |__ Images
                |__ Category_ids
            |__ Validation
                |__ Images
                |__ Category_ids

    |__ ATR
        |__ humanparsing
            |__ JPEGImages
            |__ SegmentationClassAug

|__ SUIM
    |__ train_val
        |__ images
        |__ masks
    |__ TEST
        |__ images
        |__ masks

|__ SunRGBD
    |__ SUNRGBD
        |__ kv1/kv2/realsense/xtion
    |__ SUNRGBDtoolbox
        |__ traintestSUNRGBD
            |__ allsplit.mat

|__ Mapillary
    |__ training
        |__ images
        |__ labels
    |__ validation
        |__ images
        |__ labels

|__ SmithCVPR2013_dataset_resized (HELEN)
    |__ images
    |__ labels
    |__ exemplars.txt
    |__ testing.txt
    |__ tuning.txt

|__ CelebAMask-HQ
    |__ CelebA-HQ-img
    |__ CelebAMask-HQ-mask-anno
    |__ CelebA-HQ-to-CelebA-mapping.txt

|__ LaPa
    |__ train
        |__ images
        |__ labels
    |__ val
        |__ images
        |__ labels
    |__ test
        |__ images
        |__ labels

|__ ibugmask_release
    |__ train
    |__ test

|__ FaceSynthetics
    |__ dataset_100000
    |__ dataset_1000
    |__ dataset_100

@article{xie2021segformer,
  title={SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers},
  author={Xie, Enze and Wang, Wenhai and Yu, Zhiding and Anandkumar, Anima and Alvarez, Jose M and Luo, Ping},
  journal={arXiv preprint arXiv:2105.15203},
  year={2021}
}

@misc{xiao2018unified,
  title={Unified Perceptual Parsing for Scene Understanding}, 
  author={Tete Xiao and Yingcheng Liu and Bolei Zhou and Yuning Jiang and Jian Sun},
  year={2018},
  eprint={1807.10221},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

@article{hong2021deep,
  title={Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes},
  author={Hong, Yuanduo and Pan, Huihui and Sun, Weichao and Jia, Yisong},
  journal={arXiv preprint arXiv:2101.06085},
  year={2021}
}

@misc{zhang2021rest,
  title={ResT: An Efficient Transformer for Visual Recognition}, 
  author={Qinglong Zhang and Yubin Yang},
  year={2021},
  eprint={2105.13677},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

@misc{huang2021fapn,
  title={FaPN: Feature-aligned Pyramid Network for Dense Image Prediction}, 
  author={Shihua Huang and Zhichao Lu and Ran Cheng and Cheng He},
  year={2021},
  eprint={2108.07058},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

@misc{wang2021pvtv2,
  title={PVTv2: Improved Baselines with Pyramid Vision Transformer}, 
  author={Wenhai Wang and Enze Xie and Xiang Li and Deng-Ping Fan and Kaitao Song and Ding Liang and Tong Lu and Ping Luo and Ling Shao},
  year={2021},
  eprint={2106.13797},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

@article{Liu2021PSA,
  title={Polarized Self-Attention: Towards High-quality Pixel-wise Regression},
  author={Huajun Liu and Fuqiang Liu and Xinyi Fan and Dong Huang},
  journal={Arxiv Pre-Print arXiv:2107.00782 },
  year={2021}
}

@misc{chao2019hardnet,
  title={HarDNet: A Low Memory Traffic Network}, 
  author={Ping Chao and Chao-Yang Kao and Yu-Shan Ruan and Chien-Hsiang Huang and Youn-Long Lin},
  year={2019},
  eprint={1909.00948},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

@inproceedings{sfnet,
  title={Semantic Flow for Fast and Accurate Scene Parsing},
  author={Li, Xiangtai and You, Ansheng and Zhu, Zhen and Zhao, Houlong and Yang, Maoke and Yang, Kuiyuan and Tong, Yunhai},
  booktitle={ECCV},
  year={2020}
}

@article{Li2020SRNet,
  title={Towards Efficient Scene Understanding via Squeeze Reasoning},
  author={Xiangtai Li and Xia Li and Ansheng You and Li Zhang and Guang-Liang Cheng and Kuiyuan Yang and Y. Tong and Zhouchen Lin},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.03308}
}

@ARTICLE{Yucondnet21,
  author={Yu, Changqian and Shao, Yuanjie and Gao, Changxin and Sang, Nong},
  journal={IEEE Signal Processing Letters}, 
  title={CondNet: Conditional Classifier for Scene Segmentation}, 
  year={2021},
  volume={28},
  number={},
  pages={758-762},
  doi={10.1109/LSP.2021.3070472}
}