Learn by Reasoning: Analogical Weight Generation for Few-Shot Class-Incremental Learning
This addresses the challenge of learning new classes from limited data while retaining old knowledge in incremental learning, with incremental improvements in accuracy.
The paper tackles the problem of few-shot class-incremental learning by proposing a brain-inspired analogical generative method that derives new class weights from existing classes without fine-tuning, achieving higher final and average accuracy on datasets like miniImageNet, CUB-200, and CIFAR-100 compared to state-of-the-art methods.
Few-shot class-incremental Learning (FSCIL) enables models to learn new classes from limited data while retaining performance on previously learned classes. Traditional FSCIL methods often require fine-tuning parameters with limited new class data and suffer from a separation between learning new classes and utilizing old knowledge. Inspired by the analogical learning mechanisms of the human brain, we propose a novel analogical generative method. Our approach includes the Brain-Inspired Analogical Generator (BiAG), which derives new class weights from existing classes without parameter fine-tuning during incremental stages. BiAG consists of three components: Weight Self-Attention Module (WSA), Weight & Prototype Analogical Attention Module (WPAA), and Semantic Conversion Module (SCM). SCM uses Neural Collapse theory for semantic conversion, WSA supplements new class weights, and WPAA computes analogies to generate new class weights. Experiments on miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our method achieves higher final and average accuracy compared to SOTA methods.