Research Article

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

Table 6

The result of random probability on CIFAR-100 and Mini-ImageNet with fusion operators.

Local probabilityMethods
ResNeSt50 [26]VGG16 (%) [25]VoVNet-57 (%) [24]CC-KL trainable (%) [27]CC-KL trainable with our framework (%)

CIFAR-100, Rand (0, 1)41.9346.1963.9865.5266.27
CIFAR-100, Rand (−1, 1)41.8346.2163.7865.5774.93
CIFAR-100, Rand (−2, 1)42.0346.3563.4266.1677.02
Mini-ImageNet, Rand (0, 1)40.3444.5472.6573.3974.55
Mini-ImageNet, Rand (−1, 1)40.6444.8472.5873.4781.23
Mini-ImageNet, Rand (−2, 1)41.0445.0172.4774.4585.48