Explaining the result for an image classification
Explaining the result for an image classification
Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models
arXiv paper abstract https://arxiv.org/abs/2106.01440v1
arXiv PDF paper https://arxiv.org/pdf/2106.01440v1.pdf
... Due to their black-box .., deep learning techniques are not yet widely adopted ... for ... critical domains, like healthcare and justice.
... presents Memory Wrap, a plug-and-play extension to any image classification model.
... adopting a content-attention mechanism
... outperforms standard classifiers when it learns from a limited set of data ... comparable performance when it learns from the full dataset.
... get insights about its decision process.
... test ... on ... CIFAR10, SVHN, and CINIC10.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments