Extreme vocabulary learning |
| |
Authors: | Hanze DONG Zhenfeng SUN Yanwei FU Shi ZHONG Zhengjun ZHANG Yu-Gang JIANG |
| |
Affiliation: | 1. School of Data Science, Fudan University, Shanghai 200433, China2. School of Computer Science, Fudan University, Shanghai 201203, China3. Department of Statistics, University of Wisconsin, Madison 53706, USA |
| |
Abstract: | Regarding extreme value theory, the unseen novel classes in the open-set recognition can be seen as the extreme values of training classes. Following this idea, we introduce the margin and coverage distribution to model the training classes. A novel visual-semantic embedding framework – extreme vocabulary learning (EVoL) is proposed; the EVoL embeds the visual features into semantic space in a probabilistic way. Notably, we adopt the vast open vocabulary in the semantic space to help further constraint the margin and coverage of training classes. The learned embedding can directly be used to solve supervised learning, zero-shot learning, and open set recognition simultaneously. Experiments on two benchmark datasets demonstrate the effectiveness of the proposed framework against conventional ways. |
| |
Keywords: | vocabulary-informed learning zero-shot learning extreme value theory |
|
| 点击此处可从《Frontiers of Computer Science》浏览原始摘要信息 |
|
点击此处可从《Frontiers of Computer Science》下载全文 |
|