| Status | 已發表Published |
| Zero-shot Learning With Fuzzy Attribute | |
| Liu, Chongwen; Shang, Zhaowei; Tang, Yuan Yan; IEEE | |
| 2017 | |
| Conference Name | 2017 3RD IEEE INTERNATIONAL CONFERENCE ON CYBERNETICS (CYBCONF) |
| Pages | 277-282 |
| Publication Place | 345 E 47TH ST, NEW YORK, NY 10017 USA |
| Publisher | IEEE |
| Abstract | As the zero-shot problem was proposed in machine learning field, attributes became the key point to solve zero-shot problems. The wildly used binary attribute in zero-shot learning has many limitations, and many researches had made an improvement on it. In this paper, we propose fuzzy attributes, which can describe objects better than binary attributes. We design a classifier to train the fuzzy attributes, and also consider the distance affect attribute in feature space. At last, we take experiment on AwA dataset, and the experimental results shows the fuzzy attribute can play a better performance than binary attributes in zero-shot learning. |
| URL | View the original |
| Indexed By | CPCI |
| Language | 英語English |
| WOS Research Area | Computer Science |
| WOS Subject | Computer Science, Cybernetics |
| WOS ID | WOS:000414302500045 |
| The Source to Article | WOS |
| Fulltext Access | |
| Citation statistics | |
| Document Type | Conference paper |
| Collection | University of Macau |
| Recommended Citation GB/T 7714 | Liu, Chongwen,Shang, Zhaowei,Tang, Yuan Yan,et al. Zero-shot Learning With Fuzzy Attribute[C], 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE, 2017, 277-282. |
| APA | Liu, Chongwen., Shang, Zhaowei., Tang, Yuan Yan., & IEEE (2017). Zero-shot Learning With Fuzzy Attribute. , 277-282. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment