Continuous transfer of neural network representational similarity for incremental learning.

Songsong Tian,Weijun Li,Xin Ning,Hang Ran,Hong Qin,Prayag Tiwari

Neurocomputing（2023）

引用 6|浏览10

暂无评分

摘要

•Method: Pre-trained Model Knowledge Distillation (PMKD) for incremental learning.•Feature representation knowledge transferred via PMKD.•PMKD combined with replay yields competitive performance in incremental learning.

查看译文

关键词

Incremental learning, Pre-trained model, Knowledge distillation, Neural network representation

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要