In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.
翻译:在本文中,我们致力于建立一个健全的识别系统,不断纳入新的健康班级。我们的主要目标是制定一个框架,使模型无需依赖标签数据即可更新。为此,我们提议采用代议制学习,在使用未标数据进行编码员培训的情况下,采用未标数据。这一学习框架使得能够研究和实施一个实际相关的使用案例,在持续学习的背景下,只有少量标签可供使用。我们还根据经验认为,这一框架内的类似基于代表性的学习方法,即使没有采用明确的机制防止遗忘,也能有力地忘记。我们表明,这种方法在采用自我监督的代议制学习方法时,与若干基于蒸馏的持续学习方法相比,取得了类似的业绩。