Happy++: Toward Stable and Unified Continual Generalized Category Discovery
- 1 November 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 15143-15160
Abstract
No abstract availableAll Related Versions
Funding Information
- CAS Project for Young Scientists in Basic Research (YSBR-083)
- National Natural Science Foundation of China (62320106010)
- InnoHK Program
This publication has 59 references indexed in Scilit:
- Large-Scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery2024
- SelEx: Self-expertise in Fine-Grained Generalized Category Discovery2024
- PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery2024
- Towards trustworthy dataset distillationPattern Recognition, 2024
- Novel Class Discovery Without Forgetting2022
- Class-Incremental Novel Class Discovery2022
- Open-environment machine learningNational Science Review, 2022
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955