3 papers
cs.CV2024
Neighborhood Commonality-aware Evolution Network for Continuous Generalized Category Discovery
Ye Wang, Yaxiong Wang, Guoshuai Zhao +1
Continuous Generalized Category Discovery (C-GCD) aims to continually discover novel classes from unlabelled image sets while maintaining performance on old classes. In this paper,…
cs.CV2024
Knowledge Adaptation Network for Few-Shot Class-Incremental Learning
Ye Wang, Yaxiong Wang, Guoshuai Zhao +1
Few-shot class-incremental learning (FSCIL) aims to incrementally recognize new classes using a few samples while maintaining the performance on previously learned classes. One of…
cs.LG2024
Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery
Ye Wang, Yaxiong Wang, Yujiao Wu +2
Generalized Class Discovery (GCD) aims to dynamically assign labels to unlabelled data partially based on knowledge learned from labelled data, where the unlabelled data may come f…