Discriminative Learning of Latent Features for Zero-Shot Recognition | |
Li Y(李岩)1,2; Zhang JG(张俊格)1,2; Zhang JG(张建国)3; Huang KQ(黄凯奇)1,2,4 | |
2018 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
页码 | 7463-7471 |
会议日期 | 2018.06.18-2018.06.22 |
会议地点 | Salt Lake City, USA |
摘要 | Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices aligning the visual and semantic space, whilst the importance to learn discriminative representations for ZSL is ignored. In this work, we retrospect existing methods and demonstrate the necessity to learn discriminative representations for both visual and semantic instances of ZSL. We propose an end-to-end network that is capable of 1) automatically discovering discriminative regions by a zoom network; and 2) learning discriminative semantic representations in an augmented space introduced for both user-defined and latent attributes. Our proposed method is tested extensively on two challenging ZSL datasets, and the experiment results show that the proposed method significantly outperforms state-of-the-art methods. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23344 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Huang KQ(黄凯奇) |
作者单位 | 1.中国科学院自动化研究所 2.University of Chinese Academy of Sciences 3.Computing, School of Science and Engineering, Univerisity of Dundee, UK 4.CAS Center for Excellence in Brain Science and Intelligence Technology |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li Y,Zhang JG,Zhang JG,et al. Discriminative Learning of Latent Features for Zero-Shot Recognition[C],2018:7463-7471. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
CVPR-published.pdf(1604KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论