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.

References in corpus (13)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Axiomatic Attribution for Deep Networks
• Striving for Simplicity: The All Convolutional Net
• Understanding Neural Networks Through Deep Visualization
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• SmoothGrad: removing noise by adding noise
• Object Detectors Emerge in Deep Scene CNNs
• Sanity Checks for Saliency Maps
• Towards a Definition of Disentangled Representations
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Interpreting CNN Knowledge via an Explanatory Graph
• Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs