MTUNet: Few-shot Image Classification with Visual Explanations
MTUNet: Few-shot Image Classification with Visual Explanations
复制标题
DOI：
10.1109/cvprw53098.2021.00259
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Bowen Wang;Liangzhi Li;Manisha Verma;Yuta Nakashima;R. Kawasaki;H. Nagahara
中科院分区：
文献类型：
--
作者：
Bowen Wang;Liangzhi Li;Manisha Verma;Yuta Nakashima;R. Kawasaki;H. Nagahara
几次学习(FSL)方法，主要基于神经网络，假设预先训练的知识可以从基本(见)类别获得并转移到新(看不见)类别。然而，神经网络的黑箱性质使得很难理解实际转移的是什么，这可能会阻碍其在一些风险敏感领域的应用。在本文中，我们揭示了一种新的方法来执行可解释的FSL图像分类，使用判别模式和两两匹配。实验结果表明，该方法在两个主流数据集上都能达到令人满意的解释能力。代码可用*。
Few-shot learning (FSL) approaches, mostly neural network-based, are assuming that the pre-trained knowledge can be obtained from base (seen) categories and transferred to novel (unseen) categories. However, the black-box nature of neural networks makes it difficult to understand what is actually transferred, which may hamper its application in some risk-sensitive areas. In this paper, we reveal a new way to perform explainable FSL for image classification, using discriminative patterns and pairwise matching. Experimental results prove that the proposed method can achieve satisfactory explainability on two mainstream datasets. Code is available*.