Memorizing Complementation Network for Few-Shot Class-Incremental Learning
This addresses the challenge of catastrophic forgetting and overfitting in incremental learning with few samples, which is incremental but improves specific benchmarks.
The paper tackles the problem of few-shot class-incremental learning, where models must learn new classes with limited data while avoiding forgetting old ones, by proposing a Memorizing Complementation Network and a Prototype Smoothing Hard-mining Triplet loss, achieving superior performance on benchmark datasets like CIFAR100, miniImageNet, and CUB200.
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.