← Search

Gyeong-hyeon Kim

2 accepted papers

2025

RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning

ICCV 2025poster

Prompt-based continual learning provides a rehearsal-free solution by tuning small sets of parameters while keeping pre-trained models frozen. To meet the complex demands of sequential tasks, it is crucial to integrate task-specific knowledge within prompts effectively. However, existing works rely…

Cited by 0SourcePDFScholar
2023

Growing a Brain with Sparsity-Inducing Generation for Continual Learning

ICCV 2023poster

Deep neural networks suffer from catastrophic forgetting in continual learning, where they tend to lose information about previously learned tasks when optimizing a new incoming task. Recent strategies isolate the important parameters for previous tasks to retain old knowledge while learning the new…

Cited by 7PDFcodeScholar