Improving the Performance of Deep Learning Model-Based Classification by the Analysis of Local Probability

Table 3

Result on CIFAR-100.

Methods	Zero20 (%)	Zero40 (%)	Zero80 (%)
VoVNet-57 [24]	64.23	63.85	63.6
VGG16 [25]	46.10	45.97	44.23
ResNeSt50 [26]	41.93	41.71	40.83
L-PDL-joint (our)	66.66	70.20	82.11
L-PDL-weight (our)	66.80	70.21	81.61