Conditional Variational Capsule Network for Open Set Recognition

2021 IEEE/CVF International Conference on Computer Vision (ICCV)(2021)

引用 46|浏览42
暂无评分
摘要
In open set recognition, a classifier has to detect unknown classes that are not known at training time. In order to recognize new categories, the classifier has to project the input samples of known classes in very compact and separated regions of the features space for discriminating samples of unknown classes. Recently proposed Capsule Networks have shown to outperform alternatives in many fiel...
更多
查看译文
关键词
Training,Computer vision,Image recognition,Computational modeling,Neurons,Probabilistic logic,Feature extraction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要