Visualizing Association in Exemplar-Based Classification

Taiga Kashima, Ryuichiro Hataya, Hideki NakayamaICASSP 2021 · OpenReview

Abstract

Recent progress in deep learning has enhanced image classification performance. However, classification using deep convolutional neural networks lacks interpretability. To solve this problem, we propose a novel method of explainable classification; this method uses images representing each image class, which we call exemplars. Our method comprises encoder-decoder models (association networks) and a classifier. First, the association networks transform each input image into an image that a deep neural network associates, which we call an associative image. Then, the image-level similarity between the associative images and the exemplars is used as a feature for classification. This similarity explains the decision of the classifiers. We conducted experiments using CIFAR-10, CIFAR-100, and STL-10 and demonstrated our classifier’s interpretability through the proposed visualization technique.
BibTeX
@inproceedings{kashima2021visualizing,
  author = {Taiga Kashima and Ryuichiro Hataya and Hideki Nakayama},
  title = {{Visualizing Association in Exemplar-Based Classification}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2021},
  url = {https://openreview.net/forum?id=0nId2IHOQP},
}

Loading related content...

Figure