Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to pre
(2023). Generalized continual category discovery. arXiv preprint arXiv:2308.12112. Mayilvahanan, P., Wiedemer, T., Rusak, E., Bethge, M., & Brendel, W. (2024). Does CLIP’s generalization performance mainly stem from high train-test similarity? In International conference on learning ...
Evolving Standardization for Continual Domain Generalization over Temporal Drift 5586 19:00 DreamWaltz: Make a Scene with Complex 3D Animatable Avatars 5583 17:00 Adaptive Test-Time Personalization for Federated Learning 5583 22:00 Towards Personalized Federated Learning via Heterogeneous Model Reassembly 55...
While some methods utilizing offline continual learning have been proposed for novel category discovery, they neglect the continuity of data streams in real-world settings. In this work, we introduce Online Continuous Generalized Category Discovery ( OCGCD ), which considers the dynamic nature of ...