Hello, your paper has greatly inspired me, and I have some questions about it. In general class-incremental learning scenarios, reservoir sampling is performed after training each batch. So, during the training of the first task, the data within the task will also be replayed during the training process?
Hello, your paper has greatly inspired me, and I have some questions about it. In general class-incremental learning scenarios, reservoir sampling is performed after training each batch. So, during the training of the first task, the data within the task will also be replayed during the training process?