Co-consistent regularization with discriminative feature for zero-shot learning, Proc. of Int'l Conf | |
Yanling Tian; Weitong Zhang; Qieshi Zhang; Jun Cheng; Pengyi Hao; ang Lu | |
2018 | |
会议日期 | 2018 |
会议地点 | 柬埔寨 |
英文摘要 | Abstract. With the development of deep learning, zero-shot learning(ZSL) issues deserve more attention. Due to the problems of projection domain shift and discriminative feature extraction, we propose an end-to[1]end framework, which is different from traditional ZSL methods in the following two aspects: 1) we use a cascaded network to automatically locate discriminative regions, which can better extract latent features and contribute to the representation of key semantic attributes. 2) our framework achieves mapping in visual-semantic embedding space and calculation procedure of the dot product in deep learning framework. In addition, a joint loss function is designed for the regularization constraint of the whole method and achieves supervised learning, which enhances generalization ability in test set. In this paper, we make some experiments on Animals with Attributes 2 (AwA2), Caltech-UCSD Birds 200-2011 (CUB) and SUN datasets, which achieves better results compared to the state-of-the-art methods. |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.siat.ac.cn:8080/handle/172644/13784] |
专题 | 深圳先进技术研究院_集成所 |
推荐引用方式 GB/T 7714 | Yanling Tian,Weitong Zhang,Qieshi Zhang,et al. Co-consistent regularization with discriminative feature for zero-shot learning, Proc. of Int'l Conf[C]. 见:. 柬埔寨. 2018. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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