Natural Science Foundation of China (NSFC)National Natural Science Foundation of China (NSFC) [61705170]; Natural Scie nce Foundation of Hubei ProvinceNatural Science Foundation of Hubei Province [2019CFB250]
机构署名:
本校为第一且通讯机构
院系归属:
数学与计算机学院
摘要:
When the model begins a new task, the challenge of naming the "catastrophic forgetting" limits the scalability of the deep learning network, which quickly forgets the learning capabilities it has. The fine-tuning method recommends that the original feature extraction be retained to extract the features of the new task and to achieve the purpose of learning the new class. However, this method degrades performance on previously learned tasks because the shared parameters change without new guidance for the original task-specific prediction parameters. This paper proposes general fine-tune method...