MTUNet: Few-Shot Image Classification with Visual Explanations

Bowen Wang, Liangzhi Li, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara

CVPRW 2021 pp. 2294-2298

doi:10.1109/CVPRW53098.2021.00259 /cvprw/2021/wang2021cvprw-mtunet/

Abstract

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*.

CVPRW Semantic Scholar

Cite

Text

Wang et al. "MTUNet: Few-Shot Image Classification with Visual Explanations." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00259

Markdown

[Wang et al. "MTUNet: Few-Shot Image Classification with Visual Explanations." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/wang2021cvprw-mtunet/) doi:10.1109/CVPRW53098.2021.00259

BibTeX

@inproceedings{wang2021cvprw-mtunet,
  title     = {{MTUNet: Few-Shot Image Classification with Visual Explanations}},
  author    = {Wang, Bowen and Li, Liangzhi and Verma, Manisha and Nakashima, Yuta and Kawasaki, Ryo and Nagahara, Hajime},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {2294-2298},
  doi       = {10.1109/CVPRW53098.2021.00259},
  url       = {https://mlanthology.org/cvprw/2021/wang2021cvprw-mtunet/}
}