Partitioned Memory Storage Inspired Few-Shot Class-Incremental learning
This addresses the challenge of continuous learning with limited data for AI systems, though it is an incremental improvement over existing FSCIL methods.
The paper tackles the problem of few-shot class-incremental learning by proposing a method that learns independent models for each session to prevent catastrophic forgetting, achieving state-of-the-art performance on CIFAR-100 and mini-ImageNet datasets.
Current mainstream deep learning techniques exhibit an over-reliance on extensive training data and a lack of adaptability to the dynamic world, marking a considerable disparity from human intelligence. To bridge this gap, Few-Shot Class-Incremental Learning (FSCIL) has emerged, focusing on continuous learning of new categories with limited samples without forgetting old knowledge. Existing FSCIL studies typically use a single model to learn knowledge across all sessions, inevitably leading to the stability-plasticity dilemma. Unlike machines, humans store varied knowledge in different cerebral cortices. Inspired by this characteristic, our paper aims to develop a method that learns independent models for each session. It can inherently prevent catastrophic forgetting. During the testing stage, our method integrates Uncertainty Quantification (UQ) for model deployment. Our method provides a fresh viewpoint for FSCIL and demonstrates the state-of-the-art performance on CIFAR-100 and mini-ImageNet datasets.