Research Article

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

Table 7

The introduction of the employed acronyms.

NumAcronymsIntroduction

1L-PDLOur framework, local probability-based deep learning
2CIFAR-10Dataset that is introduced in [15–17]
3Mini-ImageNetDataset that is introduced in [21–23]
4VoVNet-57A deep learning model that is introduced in [24]
5VGG16A deep learning model that is introduced in [25]
6ResNeSt50A deep learning model that is introduced in [26]
7Presents a sample
8Presents a label
9Presents the ground truth on
10Zero20Means 20% of the labels have zero samples
11Zero40Means 40% of the labels have zero samples
12Zero80Means 80% of the labels have zero samples
13L-PDL-jointJoint cooperation based on our framework, introduced in equation (4)
14L-PDL-weightWeighted cooperation based on our framework, introduced in equation (5)
15Rand (.)Is the function that outputs random value of probability
16CC-KL trainableThe existing class-conscious trainable combiner-based KL weights method that is introduced in the work [27]
17CC-KL trainable with our frameworkOur framework on class-conscious trainable combiner-based KL weights method that is introduced in the work [27]