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
  • [1] Semantic embeddings of generic objects for zero-shot learning
    Hascoet, Tristan
    Ariki, Yasuo
    Takiguchi, Tetsuya
    EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2019, 2019 (1)
  • [2] Semantic embeddings of generic objects for zero-shot learning
    Tristan Hascoet
    Yasuo Ariki
    Tetsuya Takiguchi
    EURASIP Journal on Image and Video Processing, 2019
  • [3] Haptic Zero-Shot Learning: Recognition of objects never touched before
    Abderrahmane, Zineb
    Ganesh, Gowrishankar
    Crosnier, Andre
    Cherubini, Andrea
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2018, 105 : 11 - 25
  • [4] Zero-Shot Recognition with Unreliable Attributes
    Jayaraman, Dinesh
    Grauman, Kristen
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 2014, 27
  • [5] Scalable Zero-Shot Logo Recognition
    Shulgin, Mikhail
    Makarov, Ilya
    IEEE ACCESS, 2023, 11 : 142702 - 142710
  • [6] Attribute Distillation for Zero-Shot Recognition
    Li, Houjun
    Wei, Boquan
    Computer Engineering and Applications, 60 (09): : 219 - 227
  • [7] Manifold embedding for zero-shot recognition
    Ji, Zhong
    Yu, Xuejie
    Yu, Yunlong
    He, Yuqing
    COGNITIVE SYSTEMS RESEARCH, 2019, 55 : 34 - 43
  • [8] Zero-Shot Recognition via Structured Prediction
    Zhang, Ziming
    Saligrama, Venkatesh
    COMPUTER VISION - ECCV 2016, PT VII, 2016, 9911 : 533 - 548
  • [9] An Attribute Learning Method for Zero-Shot Recognition
    Yazdanian, Ramtin
    Shojaee, Seyed Mohsen
    Baghshah, Mahdieh Soleymani
    2017 25TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2017, : 2235 - 2240
  • [10] Zero-Shot Recognition via Optimal Transport
    Wang, Wenlin
    Xu, Hongteng
    Wang, Guoyin
    Wang, Wenqi
    Carin, Lawrence
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, : 3470 - 3480