Two-level Graph Network for Few-Shot Class-Incremental Learning
This addresses the challenge of catastrophic forgetting and overfitting in incremental learning with few data points, which is crucial for real-world applications like robotics or personalized AI, though it appears incremental as it builds on existing graph-based methods for FSCIL.
The paper tackles the problem of few-shot class-incremental learning (FSCIL), where models must learn new classes from limited data without forgetting old ones, by proposing a two-level graph network (SCGN) that leverages sample-level and class-level semantic relationships, achieving state-of-the-art results on three benchmark datasets.
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbates the notorious catastrophic forgetting problems. However, existing FSCIL methods ignore the semantic relationships between sample-level and class-level. % Using the advantage that graph neural network (GNN) can mine rich information among few samples, In this paper, we designed a two-level graph network for FSCIL named Sample-level and Class-level Graph Neural Network (SCGN). Specifically, a pseudo incremental learning paradigm is designed in SCGN, which synthesizes virtual few-shot tasks as new tasks to optimize SCGN model parameters in advance. Sample-level graph network uses the relationship of a few samples to aggregate similar samples and obtains refined class-level features. Class-level graph network aims to mitigate the semantic conflict between prototype features of new classes and old classes. SCGN builds two-level graph networks to guarantee the latent semantic of each few-shot class can be effectively represented in FSCIL. Experiments on three popular benchmark datasets show that our method significantly outperforms the baselines and sets new state-of-the-art results with remarkable advantages.