A2GP-SF: Enhancing Few-shot Class Incremental Learning via Attribute Generative Prompting and Adaptive Sharpness Flattening

Abstract

Few-shot Class Incremental Learning (FSCIL) aims to incrementally learn new classes with limited examples while retaining knowledge of previously learned classes. Recent advancements in prompt tuning for large pre-trained models have shown promise in FSCIL. However, current FSCIL methods still suffer from challenges like insufficient plasticity and limited generalization. To tackle these challenges, we propose a novel prompt tuning-based framework named A2GP-SF, which integrates attribute generative prompting (AGP) and adaptive sharpness flattening (ASF). The proposed AGP paradigm dynamically generates attribute-aware prompts for each instance, facilitating better semantics learning and enhancing plasticity. Additionally, the ASF mechanism aims to mitigate overfitting by applying adaptive perturbations to flatten sharpness, with these perturbations adjusted based on gradient norm changes, thereby enhancing the model’s robustness and generalization. Extensive experiments on multiple benchmark datasets consistently demonstrate the superiority of our proposed A2GP-SF framework.