A Bag of Tricks for Few-Shot Class-Incremental Learning
This work addresses a challenging continual learning problem for AI systems that need to learn continuously from limited data, though it appears incremental as it combines existing techniques rather than introducing fundamentally new methods.
The paper tackles the problem of few-shot class-incremental learning (FSCIL), which requires continuous adaptation to new tasks with limited samples while preserving proficiency in previously learned tasks, and presents a bag of tricks framework that combines six techniques to improve stability and adaptability, achieving new state-of-the-art results on benchmark datasets like CIFAR-100, CUB-200, and miniImageNet.
We present a bag of tricks framework for few-shot class-incremental learning (FSCIL), which is a challenging form of continual learning that involves continuous adaptation to new tasks with limited samples. FSCIL requires both stability and adaptability, i.e., preserving proficiency in previously learned tasks while learning new ones. Our proposed bag of tricks brings together six key and highly influential techniques that improve stability, adaptability, and overall performance under a unified framework for FSCIL. We organize these tricks into three categories: stability tricks, adaptability tricks, and training tricks. Stability tricks aim to mitigate the forgetting of previously learned classes by enhancing the separation between the embeddings of learned classes and minimizing interference when learning new ones. On the other hand, adaptability tricks focus on the effective learning of new classes. Finally, training tricks improve the overall performance without compromising stability or adaptability. We perform extensive experiments on three benchmark datasets, CIFAR-100, CUB-200, and miniIMageNet, to evaluate the impact of our proposed framework. Our detailed analysis shows that our approach substantially improves both stability and adaptability, establishing a new state-of-the-art by outperforming prior works in the area. We believe our method provides a go-to solution and establishes a robust baseline for future research in this area.