A Bag of Tricks for Few-Shot Class-Incremental Learning

21 Mar 2024  ·  Shuvendu Roy, Chunjong Park, Aldi Fahrezi, Ali Etemad ·

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 eight 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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Few-Shot Class-Incremental Learning CIFAR-100 BOT Last Accuracy 58.75 # 2
Few-Shot Class-Incremental Learning CUB-200-2011 BOT Last Accuracy 63.75 # 2
Few-Shot Class-Incremental Learning mini-Imagenet BOT Last Accuracy 59.57 # 2

Methods