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

Table 7

The introduction of the employed acronyms.

Num	Acronyms	Introduction
1	L-PDL	Our framework, local probability-based deep learning
2	CIFAR-10	Dataset that is introduced in [15–17]
3	Mini-ImageNet	Dataset that is introduced in [21–23]
4	VoVNet-57	A deep learning model that is introduced in [24]
5	VGG16	A deep learning model that is introduced in [25]
6	ResNeSt50	A deep learning model that is introduced in [26]
7		Presents a sample
8		Presents a label
9		Presents the ground truth on
10	Zero20	Means 20% of the labels have zero samples
11	Zero40	Means 40% of the labels have zero samples
12	Zero80	Means 80% of the labels have zero samples
13	L-PDL-joint	Joint cooperation based on our framework, introduced in equation (4)
14	L-PDL-weight	Weighted cooperation based on our framework, introduced in equation (5)
15	Rand (.)	Is the function that outputs random value of probability
16	CC-KL trainable	The existing class-conscious trainable combiner-based KL weights method that is introduced in the work [27]
17	CC-KL trainable with our framework	Our framework on class-conscious trainable combiner-based KL weights method that is introduced in the work [27]