Convolutional prototype learning for zero-shot recognition
文献类型:期刊论文
作者 | Liu, Zhizhe2,3; Zhang, Xingxing2,3; Zhu, Zhenfeng2,3; Zheng, Shuai2,3; Zhao, Yao2,3; Cheng, Jian1 |
刊名 | IMAGE AND VISION COMPUTING |
出版日期 | 2020-06-01 |
卷号 | 98页码:8 |
ISSN号 | 0262-8856 |
关键词 | Zero-shot recognition Prototype learning Image recognition Deep learning |
DOI | 10.1016/j.imavis.2020.103924 |
通讯作者 | Zhu, Zhenfeng(zhfzhu@bjtu.edu.cn) |
英文摘要 | Zero-shot learning (ZSL) has received increasing attention in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors. However, the popularly learned projection functions in previous works cannot generalize well since they assume the distribution consistency between seen and unseen domains at sample-level. Besides, the provided non-visual and unique class attributes can significantly degrade the recognition performance in semantic space. In this paper, we propose a simple yet effective convolutional prototype learning (CPL) framework for zero-shot recognition. By assuming distribution consistency at task-level, our CPL is capable of transferring knowledge smoothly to recognize unseen samples. Furthermore, inside each task, discriminative visual prototypes are learned via a distance based training mechanism. Consequently, we can perform recognition in visual space, instead of semantic space. An extensive group of experiments are then carefully designed and presented, demonstrating that CPL obtains more favorable effectiveness, over currently available alternatives under various settings. (C) 2020 Elsevier B.V. All rights reserved. |
资助项目 | Science and Technology Innovation 2030 -New Generation Artificial Intelligence Major Project[2018AAA0102101] ; National Natural Science Foundation of China[61976018] ; National Natural Science Foundation of China[61532005] ; Fundamental Research Funds for the Central Universities of China[2018JBZ001] ; Fundamental Research Funds for the Central Universities of China[2019YJS048] |
WOS研究方向 | Computer Science ; Engineering ; Optics |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000536040700006 |
资助机构 | Science and Technology Innovation 2030 -New Generation Artificial Intelligence Major Project ; National Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities of China |
源URL | [http://ir.ia.ac.cn/handle/173211/39534] |
专题 | 类脑芯片与系统研究 |
通讯作者 | Zhu, Zhenfeng |
作者单位 | 1.Chinese Acad Sci, Inst Automat, NLPR, Beijing, Peoples R China 2.Beijing Key Lab Adv Informat Sci & Network Techno, Beijing, Peoples R China 3.Beijing Jiaotong Univ, Inst Informat Sci, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Zhizhe,Zhang, Xingxing,Zhu, Zhenfeng,et al. Convolutional prototype learning for zero-shot recognition[J]. IMAGE AND VISION COMPUTING,2020,98:8. |
APA | Liu, Zhizhe,Zhang, Xingxing,Zhu, Zhenfeng,Zheng, Shuai,Zhao, Yao,&Cheng, Jian.(2020).Convolutional prototype learning for zero-shot recognition.IMAGE AND VISION COMPUTING,98,8. |
MLA | Liu, Zhizhe,et al."Convolutional prototype learning for zero-shot recognition".IMAGE AND VISION COMPUTING 98(2020):8. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。