2 papers
cs.LG2024
Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning
Jiaming Liu, Hongyuan Liu, Zhili Qin +4
The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of com…
cs.CV2023
Open-world Semi-supervised Novel Class Discovery
Jiaming Liu, Yangqiming Wang, Tongze Zhang +3
Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more comple…