Encyclopedia Enhanced Semantic Embedding for Zero-Shot Learning
文献类型：会议论文
| 作者 | Jia, Zhen1,2 ; Zhang, Junge1,2; Huang, Kaiqi1,2,3; Tan, Tieniu1,2,3
|
| 出版日期 | 2017 |
| 会议日期 | 2017 September 17th-20th |
| 会议地点 | Beijing, China |
| 关键词 | Zero-shot Learning Image Classification |
| 英文摘要 | There are tremendous object categories in the real world besides those in image datasets. Zero-shot learning aims to recognize image categories which are unseen in the training set. A large number of previous zero-shot learning models use word vectors of the class labels directly as category prototypes in the semantic embedding space. But word vectors cannot obtain the global knowledge of an image category sufficiently. In this paper, we propose a new encyclopedia enhanced semantic embedding model to promote the discriminative capability of word vector prototypes with the global knowledge of each image category. The proposed model extracts the TF-IDF key words from encyclopedia articles to acquire the global knowledge of each category. The convex combination of the key words' word vectors acts as the prototypes of the object categories. The prototypes of seen and unseen classes build up the embedding space where the nearest neighbour search is implemented to recognize the unseen images. The experiments show that the proposed method achieves the state-of-the-art performance on the challenging ImageNet Fall 2011 1k2hop dataset. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/19662]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 作者单位 | 1.CRIPAC & NLPR, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
| 推荐引用方式 GB/T 7714 | Jia, Zhen,Zhang, Junge,Huang, Kaiqi,et al. Encyclopedia Enhanced Semantic Embedding for Zero-Shot Learning[C]. 见:. Beijing, China. 2017 September 17th-20th. |
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。