ELUDE: Generating interpretable explanations via a decomposition into labelled and unlabelled features. (arXiv:2206.07690v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07690

Deep learning models have achieved remarkable success in different areas of
machine learning over the past decade; however, the size and complexity of
these models make them difficult to understand. In an effort to make them more
interpretable, several recent works focus on explaining parts of a deep neural
network through human-interpretable, semantic attributes. However, it may be
impossible to completely explain complex models using only semantic attributes.
In this work, we propose to augment these attributes with a small …

arxiv cv features