Continual Learning for Classification Tasks
Han Xue-jun · 2023
The traditional machine learning models can only learn from stationary data stream and are very vulnerable to the changing environment.To encourage the machine learners to be more human-like and practical in the real-world, continual learning was put forward and attracts a surge of attention in recent few years.Conventionally, there are three scenarios in continual learning which are class-incremental, taskincremental and domain-incremental and each scenario is associated with a specific model configuration.The most critical problem addressed by continual learning is catastrophic forgetting on previously learned tasks, whereupon this thesis aims to tackle this problem for classification tasks in different continual learning settings.Towards this end, this thesis first proposes a continual learning approach with dual regularizations on output and representation spaces for domain-incremental learning.The output space is regularized by means of knowledge distillation to preserve acquired information from old tasks and the representational regularization resorts to feature selection via sparse regularizer so that the unique classifier is able to perform well in the filtered feature space.The second approach is an online continual learning algorithm applicable to all three continual learning scenarios.Specifically, the feature propagation from previous feature space to current one is employed to retain some past knowledge and a contrastive regularization loss to prevent the feature space i Dr.