Supplementary Material for ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

We adopt the memory budget used in the RMM paper [12]. In details, for each benchmark data, the memory budget is determined according to the phase number K. For instance [12], on CIFAR-10, the budget is 7k samples for K = 5 (7k samples = 10 classes per phase 500 samples per class + 2k samples). The numbers reported in Table A are duplicated from [12] where the compared methods are implemented in the same setting. The ACIL gives identical results either in growing-exemplar or fixed memory settings. This is because the ACIL does not belong to the branch of replay-based CIL.