Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains

被引:3
|
作者
Yang, Jie [1 ]
Wang, Chaoqun [1 ]
Li, Zhen [1 ]
Wang, Junle [2 ]
Zhang, Ruimao [1 ]
机构
[1] Chinese Univ Hong Kong, Shenzhen, Peoples R China
[2] Tencent, Shenzhen, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1109/CVPR52729.2023.01861
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents Scalable Semantic Transfer (SST), a novel training paradigm, to explore how to leverage the mutual benefits of the data from different label domains (i.e. various levels of label granularity) to train a powerful human parsing network. In practice, two common application scenarios are addressed, termed universal parsing and dedicated parsing, where the former aims to learn homogeneous human representations from multiple label domains and switch predictions by only using different segmentation heads, and the latter aims to learn a specific domain prediction while distilling the semantic knowledge from other domains. The proposed SST has the following appealing benefits: (1) it can capably serve as an effective training scheme to embed semantic associations of human body parts from multiple label domains into the human representation learning process; (2) it is an extensible semantic transfer framework without predetermining the overall relations of multiple label domains, which allows continuously adding human parsing datasets to promote the training. (3) the relevant modules are only used for auxiliary training and can be removed during inference, eliminating the extra reasoning cost. Experimental results demonstrate SST can effectively achieve promising universal human parsing performance as well as impressive improvements compared to its counterparts on three human parsing benchmarks (i.e., PASCAL-Person-Part, ATR, and CIHP). Code is available at https://github.com/yangjie-cv/SST.
引用
收藏
页码:19424 / 19433
页数:10
相关论文
共 50 条
  • [1] Weakly supervised image parsing via label propagation over discriminatively semantic graph
    Xu, Xiaocheng
    Ma, Jun
    Nie, Liqiang
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2016, 40 : 808 - 815
  • [2] Scalable Semantic Parsing with Partial Ontologies
    Choi, Eunsol
    Kwiatkowski, Tom
    Zettlemoyer, Luke
    [J]. PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, 2015, : 1311 - 1320
  • [3] From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding
    Wu, Shan
    Chen, Bo
    Xin, Chunlei
    Han, Xianpei
    Sun, Le
    Zhang, Weipeng
    Chen, Jiansong
    Yang, Fan
    Cai, Xunliang
    [J]. 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (ACL-IJCNLP 2021), VOL 1, 2021, : 5110 - 5121
  • [4] Semantic Parsing via Paraphrasing
    Berant, Jonathan
    Liang, Percy
    [J]. PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2014, : 1415 - 1425
  • [5] Learning Programmatic Idioms for Scalable Semantic Parsing
    Iyer, Srinivasan
    Cheung, Alvin
    Zettlemoyer, Luke
    [J]. 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 5426 - 5435
  • [6] Neural Semantic Parsing over Multiple Knowledge-bases
    Herzig, Jonathan
    Berant, Jonathan
    [J]. PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 2, 2017, : 623 - 628
  • [7] Face Illumination Transfer and Swapping via Dense Landmark and Semantic Parsing
    Jin, Xin
    Li, Zhonglan
    Ning, Ning
    Lu, Huimin
    Li, Xiaodong
    Zhang, Xiaokun
    Zhu, Xingfan
    Fang, Xi
    [J]. IEEE SENSORS JOURNAL, 2022, 22 (18) : 17391 - 17398
  • [8] Automatic image annotation via label transfer in the semantic space
    Uricchio, Tiberio
    Ballan, Lamberto
    Seidenari, Lorenzo
    Del Bimbo, Alberto
    [J]. PATTERN RECOGNITION, 2017, 71 : 144 - 157
  • [9] Controllable Semantic Parsing via Retrieval Augmentation
    Pasupat, Panupong
    Zhang, Yuan
    Guu, Kelvin
    [J]. 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 7683 - 7698
  • [10] Semantic Dependency Parsing via Book Embedding
    Sun, Weiwei
    Cao, Junjie
    Wan, Xiaojun
    [J]. PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1, 2017, : 828 - 838