Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the limited number of examples for training, the techniques developed for standard incremental learning cannot be applied verbatim to FSCIL. In this work, we introduce a distillation algorithm to address the problem of FSCIL and propose to make use of semantic information during training. To this end, we make use of word embeddings as semantic information which is cheap to obtain and which facilitate the distillation process. Furthermore, we propose a method based on an attention mechanism on multiple parallel embeddings of visual data to align visual and semantic vectors, which reduces issues related to catastrophic forgetting. Via experiments on MiniImageNet, CUB200, and CIFAR100 dataset, we establish new state-of-the-art results by outperforming existing approaches.

本研究提出一种用于解决few-shot class incremental learning（FSCIL）问题的蒸馏算法，该算法利用语义信息进行训练，同时提出基于注意机制的方法来对齐视觉和语义向量，从而有效降低了灾难性遗忘的影响，并成功地在MiniImageNet、CUB200和CIFAR100数据集上创下了新的最优结果。

基于语义感知的少样本类别增量学习知识蒸馏