Semantic Network Interpretation
Abstract
Network interpretation as an effort to reveal the features learned by a network remains largely visualization-based. In this paper, our goal is to tackle semantic network interpretation at both filter and decision level. For filter-level interpretation, we represent the concepts a filter encodes with a probability distribution of visual attributes. The decision-level interpretation is achieved by textual summarization that generates an explanatory sentence containing clues behind a network's decision. A Bayesian inference algorithm is proposed to automatically associate filters and network decisions with visual attributes. Human study confirms that the semantic interpretation is a beneficial alternative or complement to visualization methods. We demonstrate the crucial role that semantic network interpretation can play in understanding a network's failure patterns. More importantly, semantic network interpretation enables a better understanding of the correlation between a model's performance and its distribution metrics like filter selectivity and concept sparseness.
Cite
@article{arxiv.1805.08969,
title = {Semantic Network Interpretation},
author = {Pei Guo and Ryan Farrell},
journal= {arXiv preprint arXiv:1805.08969},
year = {2021}
}