Revisiting Document Representations for Large-Scale Zero-Shot Learning

被引:0
|
作者
Kil, Jihyung [1 ]
Chao, Wei-Lun [1 ]
机构
[1] Ohio State Univ, Columbus, OH 43210 USA
关键词
D O I
暂无
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 aims to recognize unseen objects using their semantic representations. Most existing works use visual attributes labeled by humans, not suitable for large-scale applications. In this paper, we revisit the use of documents as semantic representations. We argue that documents like Wikipedia pages contain rich visual information, which however can easily be buried by the vast amount of non-visual sentences. To address this issue, we propose a semi-automatic mechanism for visual sentence extraction that leverages the document section headers and the clustering structure of visual sentences. The extracted visual sentences, after a novel weighting scheme to distinguish similar classes, essentially form semantic representations like visual attributes but need much less human effort. On the ImageNet dataset with over 10,000 unseen classes, our representations lead to a 64% relative improvement against the commonly used ones.
引用
收藏
页码:3117 / 3128
页数:12
相关论文
共 50 条
  • [1] A Large-scale Attribute Dataset for Zero-shot Learning
    Zhao, Bo
    Fu, Yanwei
    Liang, Rui
    Wu, Jiahong
    Wang, Yonggang
    Wang, Yizhou
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 398 - 407
  • [2] Semantic guided knowledge graph for large-scale zero-shot learning
    Wei, Jiwei
    Sun, Haotian
    Yang, Yang
    Xu, Xing
    Li, Jingjing
    Shen, Heng Tao
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2022, 88
  • [3] Large-scale zero-shot learning in the wild: Classifying zoological illustrations
    Stork, Lise
    Weber, Andreas
    van den Herik, Jaap
    Plaat, Aske
    Verbeek, Fons
    Wolstencroft, Katherine
    [J]. ECOLOGICAL INFORMATICS, 2021, 62
  • [4] Evaluating Knowledge Transfer and Zero-Shot Learning in a Large-Scale Setting
    Rohrbach, Marcus
    Stark, Michael
    Schiele, Bernt
    [J]. 2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011, : 1641 - 1648
  • [5] Learning MLatent Representations for Generalized Zero-Shot Learning
    Ye, Yalan
    Pan, Tongjie
    Luo, Tonghoujun
    Li, Jingjing
    Shen, Heng Tao
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 2252 - 2265
  • [6] High efficient framework for large-scale zero-shot image recognition
    Zhang, Zehuan
    Liu, Qiang
    Guo, Difei
    [J]. Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University, 2022, 49 (06): : 103 - 110
  • [7] Semantic Concept Discovery for Large-Scale Zero-Shot Event Detection
    Chang, Xiaojun
    Yang, Yi
    Hauptmann, Alexander G.
    Xing, Eric P.
    Yu, Yao-Liang
    [J]. PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI), 2015, : 2234 - 2240
  • [8] Learning Invariant Visual Representations for Compositional Zero-Shot Learning
    Zhang, Tian
    Liang, Kongming
    Du, Ruoyi
    Sun, Xian
    Ma, Zhanyu
    Guo, Jun
    [J]. COMPUTER VISION, ECCV 2022, PT XXIV, 2022, 13684 : 339 - 355
  • [9] Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification
    Yi, Kai
    Shen, Xiaoqian
    Gou, Yunhao
    Elhoseiny, Mohamed
    [J]. COMPUTER VISION, ECCV 2022, PT XX, 2022, 13680 : 116 - 132
  • [10] Learning Modality-Invariant Latent Representations for Generalized Zero-shot Learning
    Li, Jingjing
    Jing, Mengmeng
    Zhu, Lei
    Ding, Zhengming
    Lu, Ke
    Yang, Yang
    [J]. MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 1348 - 1356