Visualizing Association in Exemplar-Based Classification
| Autor: | Ryuichiro Hataya, Taiga Kashima, Hideki Nakayama |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
Contextual image classification Computer science business.industry Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Convolutional neural network Visualization ComputingMethodologies_PATTERNRECOGNITION Feature (computer vision) Classifier (linguistics) Artificial intelligence business Interpretability |
| Zdroj: | ICASSP |
| DOI: | 10.1109/icassp39728.2021.9413574 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|