Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition

被引:0
|
作者
Chai, Chunlai [1 ]
Lou, Yukuan [1 ]
Zhang, Shijin [1 ]
Hua, Ming [2 ]
机构
[1] Zhejiang Gongshang Univ, Hangzhou, Peoples R China
[2] Oakland Univ, Rochester, MI 48063 USA
来源
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) | 2021年
关键词
Zero-shot learning; Potential discrimination space generation; Attribute correlation;
D O I
10.1109/ICPR48806.2021.9413287
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Zero-shot learning (ZSL) aims to recognize unseen classes accurately by learning seen classes and known attributes, but correlations in attributes were ignored by previous study which lead to classification results confused. To solve this problem, we build an Attribute Correlation Potential Space Generation (ACPSG) model which uses a graph convolution network and attribute correlation to generate a more discriminating potential space. Combining potential discrimination space and user-defined attribute space, we can better classify unseen classes. Our approach outperforms some existing state-of-the-art methods on several benchmark datasets, whether it is conventional ZSL or generalized ZSL.
引用
收藏
页码:4751 / 4757
页数:7
相关论文
共 50 条
  • [1] Transductive Learning With Prior Knowledge for Generalized Zero-Shot Action Recognition
    Su, Taiyi
    Wang, Hanli
    Qi, Qiuping
    Wang, Lei
    He, Bin
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (01) : 260 - 273
  • [2] Zero-shot recognition with latent visual attributes learning
    Xie, Yurui
    He, Xiaohai
    Zhang, Jing
    Luo, Xiaodong
    MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (37-38) : 27321 - 27335
  • [3] Zero-shot recognition with latent visual attributes learning
    Yurui Xie
    Xiaohai He
    Jing Zhang
    Xiaodong Luo
    Multimedia Tools and Applications, 2020, 79 : 27321 - 27335
  • [4] Zero-Shot Recognition with Unreliable Attributes
    Jayaraman, Dinesh
    Grauman, Kristen
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 2014, 27
  • [5] Grouping attributes zero-shot learning for tongue constitution recognition
    Wen, Guihua
    Ma, Jiajiong
    Hu, Yang
    Li, Huihui
    Jiang, Lijun
    ARTIFICIAL INTELLIGENCE IN MEDICINE, 2020, 109
  • [6] Beyond Semantic Attributes: Discrete Latent Attributes Learning for Zero-Shot Recognition
    Qin, Jie
    Wang, Yunhong
    Liu, Li
    Chen, Jiaxin
    Shao, Ling
    IEEE SIGNAL PROCESSING LETTERS, 2016, 23 (11) : 1667 - 1671
  • [7] Semantic-aware visual attributes learning for zero-shot recognition
    Xie, Yurui
    Song, Tiecheng
    Li, Wei
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2021, 74 (74)
  • [8] Semantic-aware visual attributes learning for zero-shot recognition
    Xie, Yurui
    Song, Tiecheng
    Li, Wei
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2021, 74
  • [9] Semantic-aware visual attributes learning for zero-shot recognition
    Xie, Yurui
    Song, Tiecheng
    Li, Wei
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2021, 74
  • [10] Semantic-aware visual attributes learning for zero-shot recognition
    Xie, Yurui
    Song, Tiecheng
    Li, Wei
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2021, 74