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
  • [21] Visual Context Embeddings for Zero-Shot Recognition
    Cho, Gunhee
    Choi, Yong Suk
    37TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, 2022, : 1039 - 1047
  • [22] Zero-shot action recognition in videos: A survey
    Estevam, Valter
    Pedrini, Helio
    Menotti, David
    NEUROCOMPUTING, 2021, 439 : 159 - 175
  • [23] Towards Zero-Shot Sign Language Recognition
    Bilge, Yunus Can
    Cinbis, Ramazan Gokberk
    Ikizler-Cinbis, Nazli
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (01) : 1217 - 1232
  • [24] Hierarchical Prototype Learning for Zero-Shot Recognition
    Zhang, Xingxing
    Gui, Shupeng
    Zhu, Zhenfeng
    Zhao, Yao
    Liu, Ji
    IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 22 (07) : 1692 - 1703
  • [25] Context-Aware Zero-Shot Recognition
    Luo, Ruotian
    Zhang, Ning
    Han, Bohyung
    Yang, Linjie
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 11709 - 11716
  • [26] A causal view of compositional zero-shot recognition
    Atzmon, Yuval
    Kreuk, Felix
    Shalit, Uri
    Chechik, Gal
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS (NEURIPS 2020), 2020, 33
  • [27] Adaptive Metric Learning For Zero-Shot Recognition
    Jiang, Huajie
    Wang, Ruiping
    Shan, Shiguang
    Chen, Xilin
    IEEE SIGNAL PROCESSING LETTERS, 2019, 26 (09) : 1270 - 1274
  • [28] Elaborative Rehearsal for Zero-shot Action Recognition
    Chen, Shizhe
    Huang, Dong
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 13618 - 13627
  • [29] FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior
    Chen, Zhekai
    Wang, Wen
    Yang, Zhen
    Yuan, Zeqing
    Chen, Hao
    Shen, Chunhua
    COMPUTER VISION - ECCV 2024, PT XVII, 2025, 15075 : 70 - 87
  • [30] A Generative Approach to Zero-Shot and Few-Shot Action Recognition
    Mishra, Ashish
    Verma, Vinay Kumar
    Reddy, M. Shiva Krishna
    Arulkumar, S.
    Rai, Piyush
    Mittal, Anurag
    2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, : 372 - 380