1 code implementation • 31 Aug 2020 • Yang Yang, Zhen-Qiang Sun, HengShu Zhu, Yanjie Fu, Hui Xiong, Jian Yang
To this end, we propose a Class-Incremental Learning without Forgetting (CILF) framework, which aims to learn adaptive embedding for processing novel class detection and model update in a unified framework.
no code implementations • 11 Aug 2020 • Yang Yang, Zhen-Qiang Sun, Hui Xiong, Jian Yang
Open set classification (OSC) tackles the problem of determining whether the data are in-class or out-of-class during inference, when only provided with a set of in-class examples at training time.