Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning

被引:2
作者
Lee, Jeong-Cheol [1 ]
Shibu, Athul [1 ]
Lee, Dong-Gyu [1 ]
机构
[1] Kyungpook Natl Univ, Dept Artificial Intelligence, Daegu, South Korea
来源
2023 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, ICCE | 2023年
基金
新加坡国家研究基金会;
关键词
Adaptive margin; contrastive network; deep learning; generalized zero-shot learning; zero-shot learning;
D O I
10.1109/ICCE56470.2023.10043553
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Generalized zero-shot learning is a challenging problem that aims to recognize images from seen and unseen classes. Recent methods are costly and time-consuming or have a bias problem. To tackle this problem, we proposed an adaptive margin-based contrastive network that aims to distinguish similar classes in generalized zero-shot learning. The proposed method employs the architecture of transferable contrastive network to classify unseen classes and adaptive margin to transfer discriminative knowledge. Experiments on the AwA2 dataset demonstrate competitive results against state-of-the-art benchmarks.
引用
收藏
页数:4
相关论文
共 50 条
[31]   Semantic Fusion and Contrastive Generation for Generalized Zero-Shot LearningSemantic Fusion and Contrastive Generation for Generalized Zero-Shot LearningG. Yang et al. [J].
Guan Yang ;
Weihao Sun ;
Xiaoming Liu ;
Yang Liu ;
Chen Wang .
International Journal of Multimedia Information Retrieval, 2025, 14 (3)
[32]   Semantic-Guided Prompt Learning Network for Generalized Zero-Shot Learning [J].
Hu, Yongli ;
Feng, Lincong ;
Jiang, Huajie ;
Liu, Mengting ;
Yin, Baocai .
COMPUTER ANIMATION AND SOCIAL AGENTS, CASA 2024, PT I, 2025, 2374 :241-253
[33]   Domain-Aware Prototype Network for Generalized Zero-Shot Learning [J].
Hu, Yongli ;
Feng, Lincong ;
Jiang, Huajie ;
Liu, Mengting ;
Yin, Baocai .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (05) :3180-3191
[34]   Cross-modal propagation network for generalized zero-shot learning [J].
Guo, Ting ;
Liang, Jianqing ;
Liang, Jiye ;
Xie, Guo-Sen .
PATTERN RECOGNITION LETTERS, 2022, 159 :125-131
[35]   Triple Loss Based Framework for Generalized Zero-Shot Learning [J].
Shen, Yaying ;
Li, Qun ;
Xu, Ding ;
Zhang, Ziyi ;
Yang, Rui .
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2022, E105D (04) :832-835
[36]   Model Selection for Generalized Zero-Shot Learning [J].
Zhang, Hongguang ;
Koniusz, Piotr .
COMPUTER VISION - ECCV 2018 WORKSHOPS, PT II, 2019, 11130 :198-204
[37]   Dual insurance for generalized zero-shot learning [J].
Liang, Jiahao ;
Fang, Xiaozhao ;
Kang, Peipei ;
Han, Na ;
Li, Chuang .
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2025, 16 (03) :2111-2125
[38]   Learning MLatent Representations for Generalized Zero-Shot Learning [J].
Ye, Yalan ;
Pan, Tongjie ;
Luo, Tonghoujun ;
Li, Jingjing ;
Shen, Heng Tao .
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 :2252-2265
[39]   Learning the Compositional Domains for Generalized Zero-shot Learning [J].
Dong, Hanze ;
Fu, Yanwei ;
Hwang, Sung Ju ;
Sigal, Leonid ;
Xue, Xiangyang .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2022, 221
[40]   Zero-Shot Pill-Prescription Matching With Graph Convolutional Network and Contrastive Learning [J].
Nguyen, Trung Thanh ;
Nguyen, Phi Le ;
Kawanishi, Yasutomo ;
Komamizu, Takahiro ;
Ide, Ichiro .
IEEE ACCESS, 2024, 12 :55889-55904