Memorizing Complementation Network for Few-Shot Class-Incremental Learning
IEEE Transactions on Image Processing(2023)
摘要
Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems. The inaccessibility of old classes and the scarcity of the novel samples make it formidable to realize the trade-off between retaining old knowledge and learning novel concepts. Inspired by that different models memorize different knowledge when learning novel concepts, we propose a Memorizing Complementation Network (MCNet) to ensemble multiple models that complements the different memorized knowledge with each other in novel tasks. Additionally, to update the model with few novel samples, we develop a Prototype Smoothing Hard-mining Triplet (PSHT) loss to push the novel samples away from not only each other in current task but also the old distribution. Extensive experiments on three benchmark datasets, e.g., CIFAR100, miniImageNet and CUB200, have demonstrated the superiority of our proposed method.
更多查看译文
关键词
Task analysis,Power capacitors,Ensemble learning,Knowledge engineering,Feature extraction,Adaptation models,Training,Few-shot learning,class-incremental learning,ensemble learning,memorizing complementation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络