Class Incremental Learning (CIL) aims to enable machines to continuously acquire new knowledge without forgetting previously learned concepts. However, existing methods primarily rely on discriminative parameter expansion, making them highly prone to catastrophic forgetting due to parameter overwriting. Furthermore, th...
Han-Yuan Ge, Bo Ren, Xin-Yi Wang et al.· Proceedings of the 34th ACM...· 0 citations
Dynamic Earth observation applications often require land-cover segmentation models to recognize newly emerging classes from only a few pixel-level annotations while retaining previously learned knowledge. However, gradient-based incremental fine-tuning (FT) is prone to severe overfitting and catastrophic forgetting un...
Han-Yuan Ge, Bo Ren, Junxi Guo et al.· IEEE Transactions on Geoscie...· 0 citations
A multimodal knowledge-driven framework that supports question answering on standard knowledge named BEST-KAG (Knowledge-Augmented Generation for Building Engineering STandards), which consistently outperforms multiple mainstream LLMs in terms of Expert evaluation, and metrics including BLEU, and ROUGE.
Jiarui Lin, Junxi Guo, Ke-Yin Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.