OntoZSL: Ontology-enhanced Zero-shot Learning

被引:34
|
作者
Geng, Yuxia [1 ]
Chen, Jiaoyan [2 ]
Chen, Zhuo [1 ]
Pan, Jeff Z. [3 ]
Ye, Zhiquan [4 ]
Yuan, Zonggang [5 ]
Jia, Yantao [6 ]
Chen, Huajun [7 ,8 ]
机构
[1] Zhejiang Univ, Hangzhou, Peoples R China
[2] Univ Oxford, Oxford, England
[3] Univ Edinburgh, Edinburgh, Midlothian, Scotland
[4] Zhejiang Univ, Coll Comp Sci, Hangzhou, Peoples R China
[5] Huawei Technol Co Ltd, NAIE CTO Off, Nanjing, Peoples R China
[6] Huawei Technol Co Ltd, Poisson Lab, Beijing, Peoples R China
[7] Zhejiang Univ, Coll Comp Sci, AZFT Knowledge Engine Lab, Hangzhou, Peoples R China
[8] Zhejiang Univ, HIC, AZFT Knowledge Engine Lab, Hangzhou, Peoples R China
关键词
Zero-shot Learning; Ontology; Generative Adversarial Networks; Image Classification; Knowledge Graph Completion; CLASSIFICATION;
D O I
10.1145/3442381.3450042
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), which aims to predict for those classes that have never appeared in the training data, has arisen hot research interests. The key of implementing ZSL is to leverage the prior knowledge of classes which builds the semantic relationship between classes and enables the transfer of the learned models (e.g., features) from training classes (i.e., seen classes) to unseen classes. However, the priors adopted by the existing methods are relatively limited with incomplete semantics. In this paper, we explore richer and more competitive prior knowledge to model the inter-class relationship for ZSL via ontology-based knowledge representation and semantic embedding. Meanwhile, to address the data imbalance between seen classes and unseen classes, we developed a generative ZSL framework with Generative Adversarial Networks (GANs). Our main findings include: (i) an ontology-enhanced ZSL framework that can be applied to different domains, such as image classification (IMGC) and knowledge graph completion (KGC); (ii) a comprehensive evaluation with multiple zero-shot datasets from different domains, where our method often achieves better performance than the state-of-the-art models. In particular, on four representative ZSL baselines of IMGC, the ontology-based class semantics outperform the previous priors e.g., the word embeddings of classes by an average of 12.4 accuracy points in the standard ZSL across two example datasets (see Figure 4).
引用
收藏
页码:3325 / 3336
页数:12
相关论文
共 50 条
  • [21] Practical Aspects of Zero-Shot Learning
    Saad, Elie
    Paprzycki, Marcin
    Ganzha, Maria
    COMPUTATIONAL SCIENCE, ICCS 2022, PT II, 2022, : 88 - 95
  • [22] Zero-Shot Program Representation Learning
    Cui, Nan
    Jiang, Yuze
    Gu, Xiaodong
    Shen, Beijun
    30TH IEEE/ACM INTERNATIONAL CONFERENCE ON PROGRAM COMPREHENSION (ICPC 2022), 2022, : 60 - 70
  • [23] Research progress of zero-shot learning
    Sun, Xiaohong
    Gu, Jinan
    Sun, Hongying
    APPLIED INTELLIGENCE, 2021, 51 (06) : 3600 - 3614
  • [24] Research progress of zero-shot learning
    Xiaohong Sun
    Jinan Gu
    Hongying Sun
    Applied Intelligence, 2021, 51 : 3600 - 3614
  • [25] Joint Dictionaries for Zero-Shot Learning
    Kolouri, Soheil
    Rostami, Mohammad
    Owechko, Yuri
    Kim, Kyungnam
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 3431 - 3439
  • [26] Creativity Inspired Zero-Shot Learning
    Elhoseiny, Mohamed
    Elfeki, Mohamed
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 5783 - 5792
  • [27] Synthesized Classifiers for Zero-Shot Learning
    Changpinyo, Soravit
    Chao, Wei-Lun
    Gong, Boqing
    Sha, Fei
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 5327 - 5336
  • [28] Zero-Shot Learning With Transferred Samples
    Guo, Yuchen
    Ding, Guiguang
    Han, Jungong
    Gao, Yue
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (07) : 3277 - 3290
  • [29] LVQ Treatment for Zero-Shot Learning
    Ismailoglu, Firat
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2023, 31 (01) : 216 - 237
  • [30] Attribute subspaces for zero-shot learning
    Zhou, Lei
    Liu, Yang
    Bai, Xiao
    Li, Na
    Yu, Xiaohan
    Zhou, Jun
    Hancock, Edwin R.
    PATTERN RECOGNITION, 2023, 144