no code implementations • 11 Nov 2018 • K. Sai Ram, Jayanta Mukherjee, Amit Patra, Partha Pratim Das
We report accuracies up to $85. 6\%$ ( $94. 75\%$ ) on scenarios with 13 ( 4 ) classes of CIFAR100, using a pre-trained VGG-16 network on the full data set.