Few-shot class-incremental learning (FSCIL), which targets at continuously expanding model's representation capacity under few supervisions, is an important yet challenging problem. On the one hand, when fitting new tasks (novel classes), features trained on old tasks (old classes) could significantly drift, causing catastrophic forgetting. On the other hand, training the large amount of model parameters with few-shot novel-class examples leads to model over-fitting. In this paper, we propose a learnable expansion-and-compression network (LEC-Net), with the aim to simultaneously solve catastrophic forgetting and model over-fitting problems in a unified framework. By tentatively expanding network nodes, LEC-Net enlarges the representation capacity of features, alleviating feature drift of old network from the perspective of model regularization. By compressing the expanded network nodes, LEC-Net purses minimal increase of model parameters, alleviating over-fitting of the expanded network from a perspective of compact representation. Experiments on the CUB/CIFAR-100 datasets show that LEC-Net improves the baseline by 5~7% while outperforms the state-of-the-art by 5~6%. LEC-Net also demonstrates the potential to be a general incremental learning approach with dynamic model expansion capability.
翻译:少见的班级强化学习(FSCIL)的目标是在少数监管下不断扩展模型代表能力,这是一个重要而具有挑战性的问题。一方面,在安装新任务(新课程)时,对旧任务(旧班)进行训练后的特点可能会大幅转移,造成灾难性的遗忘。另一方面,对大量模型参数进行培训,采用少见的新颖类实例,导致模型过度适用。在本文件中,我们提议建立一个可学习的扩展和压缩网络(LEC-Net),目的是同时解决灾难性的遗忘和在统一框架内的建模问题。LEC-Net通过暂时扩展网络节点,扩大了功能的代表性,从模式正规化的角度减轻旧网络的特征漂移。通过压缩扩大的网络节点,LEC-Net钱包最低限度地增加模型参数,从压缩的角度减轻扩大的网络的过度配置。CUB/CIFAR-100数据集的实验显示,LEC-Net将基准改善5-7 %的基线,同时以进步的模型取代了LEC-Net的开发能力。