EW-CACTUs-MAML: A Robust Metalearning System for Rapid Classification on a Large Number of Tasks

Table 2

Comparisons of the performance of EW-CACTUs-ProtoNets and CACTUs-ProtoNets on Miniimagenet with k = 100 for each partition.

Dataset	Algorithm	Train loss	Train acc (%)	Val loss	Val acc (%)
Miniimagenet (5-way/1-shot)	EW-CACTUs-ProtoNets	0.8724325	68.35	1.344944	48.52
	CACTUs-ProtoNets	0.8353898	68.86	1.3138521	48.78