On zero-shot recognition of generic objects

被引:6
|
作者
Hascoet, Tristan [1 ]
Ariki, Yasuo [1 ]
Takiguchi, Tetsuya [1 ]
机构
[1] Kobe Univ, Grad Sch Syst Informat, Kobe, Hyogo, Japan
关键词
D O I
10.1109/CVPR.2019.00978
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many recent advances in computer vision are the result of a healthy competition among researchers on high quality, task-specific, benchmarks. After a decade of active research, zero-shot learning (ZSL) models accuracy on the Imagenet benchmark remains far too low to be considered for practical object recognition applications. In this paper, we argue that the main reason behind this apparent lack of progress is the poor quality of this benchmark. We highlight major structural flaws of the current benchmark and analyze different factors impacting the accuracy of ZSL models. We show that the actual classification accuracy of existing ZSL models is significantly higher than was previously thought as we account for these flaws. We then introduce the notion of structural bias specific to ZSL datasets. We discuss how the presence of this new form of bias allows for a trivial solution to the standard benchmark and conclude on the need for a new benchmark. We then detail the semi-automated construction of a new benchmark to address these flaws.
引用
收藏
页码:9545 / 9553
页数:9
相关论文
共 50 条
  • [31] Hierarchical Prompt Learning for Compositional Zero-Shot Recognition
    Wang, Henan
    Yang, Muli
    Wei, Kun
    Deng, Cheng
    PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 1470 - 1478
  • [32] Zero-Shot Visual Emotion Recognition by Exploiting BERT
    Kang, Hyunwook
    Hazarika, Devamanyu
    Kim, Dongho
    Kim, Jihie
    INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 2, 2023, 543 : 485 - 494
  • [33] Discriminative Learning of Latent Features for Zero-Shot Recognition
    Li, Yan
    Zhang, Junge
    Zhang, Jianguo
    Huang, Kaiqi
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 7463 - 7471
  • [34] Zero-Shot Object Recognition by Semantic Manifold Distance
    Fu, Zhenyong
    Xiang, Tao
    Kodirov, Elyor
    Gong, Shaogang
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 2635 - 2644
  • [35] 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
  • [36] A ZERO-SHOT ARCHITECTURE FOR ACTION RECOGNITION IN STILL IMAGES
    Safaei, Marjaneh
    Foroosh, Hassan
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 460 - 464
  • [37] Variational Autoencoder for Zero-Shot Recognition of Bai Characters
    Lin, Weiwei
    Ma, Tai
    Zhang, Zeqing
    Li, Xiaofan
    Xue, Xingsi
    Wireless Communications and Mobile Computing, 2022, 2022
  • [38] Deconfounding Causal Inference for Zero-Shot Action Recognition
    Wang, Junyan
    Jiang, Yiqi
    Long, Yang
    Sun, Xiuyu
    Pagnucco, Maurice
    Song, Yang
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 3976 - 3986
  • [39] ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
    Zhang, Xingxing
    Gui, Shupeng
    Jin, Jian
    Zhu, Zhenfeng
    Zhao, Yao
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 15 - 27
  • [40] Hyperbolic Visual Embedding Learning for Zero-Shot Recognition
    Liu, Shaoteng
    Chen, Jingjing
    Pan, Liangming
    Ngo, Chong-Wah
    Chua, Tat-Seng
    Jiang, Yu-Gang
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, : 9270 - 9278