result for 'scenario = class' about brain-inspired-replay HOT 2 CLOSED

1.) The use of the term ‘task’ in the class-incremental learning scenario is indeed confusing; the term ‘episode’ would be more appropriate.
The results that are printed to the screen at the end of training are indeed for the Class-IL scenario (i.e., using a single-head classifier). For example, the reported accuracy for “task 1” is the average accuracy of the final model for the test data from task 1 (e.g., all the test samples that are ‘0’s and ‘1’s for split-MNIST), but whereby the model had to choose between all possible classes (e.g., a 10-way classification for split-MNIST).

2.) Yes, that EWC, SI and LwF have almost no effect when they are trained and evaluated according the Class-IL scenario is indeed what I would expect. That’s what I found as well.

Hope this helps!

from brain-inspired-replay.

Many thanks for you! It helps a lot！

from brain-inspired-replay.