基于张量特征的小样本图像快速分类方法

张艳莎, 冯夫健, 王杰, 潘凤, 谭棉, 张再军, 王林

Tensor feature⁃based faster classification network for few⁃shot learning

Yansha Zhang, Fujian Feng, Jie Wang, Feng Pan, Mian Tan, Zaijun Zhang, Lin Wang

表5 在不同分类器上的实验结果对比

Table 5 Experimental results by various classifiers

Method Backbone Logistic Regression Support Vector Machine miniImageNet CUB miniImageNet CUB 1⁃shot 5⁃shot 1⁃shot 5⁃shot 1⁃shot 5⁃shot 1⁃shot 5⁃shot Baseline(1) ResNet⁃18 59.20±0.82 77.71±0.61 69.44±0.86 86.19±0.49 57.12±0.84 76.45±0.62 67.24±0.87 84.72±0.52 Baseline⁃KD(2) ResNet⁃18 61.83±0.82 79.27±0.61 72.74±0.88 87.71±0.49 60.21±0.84 78.28±0.61 71.23±0.89 86.34±0.52 TFFCN ResNet⁃18 63.92±0.81 79.84±0.61 74.82±0.87 88.43±0.47 64.01± 0.80 79.50±0.60 75.40±0.85 88.44±0.47