Supplementary Material: Calibrating CNNs for Lifelong Learning

ResNet-18(1/3) is simply ResNet-18 [1], with the number of filters in each layer reduced by 3 times [2]. We use SGD optimizer in all our experiments. In all cases, we run experiments for 5 random task orders and report the average accuracy. From the results, we can see that even with ResNet-18(1/3), which has lesser parameters than ResNet-18, results are comparable for CCLL<1,1> model. CCLL<4,1> with ResNet-18(1/3) performs even better as compared to CCLL<1,1> with ResNet-18.