Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks
arXiv:1807.11720 · doi:10.1109/ACCESS.2019.2963055
Abstract
Recently, many methods to interpret and visualize deep neural network predictions have been proposed and significant progress has been made. However, a more class-discriminative and visually pleasing explanation is required. Thus, this paper proposes a region-based approach that estimates feature importance in terms of appropriately segmented regions. By fusing the saliency maps generated from multi-scale segmentations, a more class-discriminative and visually pleasing map is obtained. We incorporate this regional multi-scale concept into a prediction difference method that is model-agnostic. An input image is segmented in several scales using the super-pixel method, and exclusion of a region is simulated by sampling a normal distribution constructed using the boundary prior. The experimental results demonstrate that the regional multi-scale method produces much more class-discriminative and visually pleasing saliency maps.
arXiv comment9 pages, 5 figures, submitted on NIPS 2018
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Methods for Interpreting and Understanding Deep Neural Networks
- Learning Important Features Through Propagating Activation Differences
- European Union regulations on algorithmic decision-making and a "right to explanation"
- Understanding Neural Networks Through Deep Visualization
- Interpretable Explanations of Black Boxes by Meaningful Perturbation
- Superpixels: An Evaluation of the State-of-the-Art
- Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
- InterpNET: Neural Introspection for Interpretable Deep Learning
- Improving Interpretability of Deep Neural Networks with Semantic Information