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4 在不同数据集上的实验结果对比

Table 4 Experimental results on various datasets

Method	Backbone	miniImageNet		CUB		CIFAR⁃FS
Method	Backbone	1⁃shot	5⁃shot	1⁃shot	5⁃shot	1⁃shot	5⁃shot
Baseline(1)	ResNet⁃18	56.81±_0.81	78.31±_0.59	67.14±_0.89	86.22±_0.50	65.71±_0.95	84.68±_0.61
Baseline⁃KD(2)	ResNet⁃18	59.62±_0.85	79.31±_0.62	70.85±_0.90	87.64±_0.48	69.15±_0.94	85.89±_0.59
TFFCN	ResNet⁃18	63.99±_0.80	79.95±_0.61	75.13±_0.86	88.08±_0.47	73.00±_0.95	86.52±_0.62