基于特征类内紧凑性的不平衡医学图像分类方法

孟元, 张轶哲, 张功萱, 宋辉

Imbalanced medical image classification based on intra⁃class compactness of features

Yuan Meng, Yizhe Zhang, Gongxuan Zhang, Hui Song

表3 在EyePacs数据集上的实验结果

Table 3 Experimental results of different algorithms on the EyePacs dataset

模型 原模型 原模型+ZC3NC Balanced ACC Weighted⁃P Balanced ACC Weighted⁃P Avg 47.89% 73.16% 51.25% 73.27% ResNet18 47.19% 72.48% 51.11% 72.54% ResNet50 47.70% 73.65% 51.92% 73.94% ResNeXt50 48.19% 73.93% 52.34% 74.39% GoogLeNet 48.46% 72.57% 49.63% 72.22%