Regional Multi-Scale Approach for Visually Pleasing Explanations of Deep Neural Networks

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. This paper incorporates this regional multi-scale concept into a prediction difference method that is model-agnostic. An input image is segmented in several scales using the superpixel method, and exclusion of a region is simulated by sampling a normal distribution constructed via the boundary prior. The experimental results demonstrate that the regional multi-scale method produces much more class-discriminative and visually pleasing saliency maps.

[1]  Bo Zhang,et al.  Improving Interpretability of Deep Neural Networks with Semantic Information , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Marko Robnik-Sikonja,et al.  Explaining Classifications For Individual Instances , 2008, IEEE Transactions on Knowledge and Data Engineering.

[3]  Max Welling,et al.  Visualizing Deep Neural Network Decisions: Prediction Difference Analysis , 2017, ICLR.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[6]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[8]  Wojciech Samek,et al.  Methods for interpreting and understanding deep neural networks , 2017, Digit. Signal Process..

[9]  H. Braak,et al.  Neuropathological stageing of Alzheimer-related changes , 2004, Acta Neuropathologica.

[10]  Hod Lipson,et al.  Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.

[11]  Rama Chellappa,et al.  Entropy rate superpixel segmentation , 2011, CVPR 2011.

[12]  Andrea Vedaldi,et al.  Interpretable Explanations of Black Boxes by Meaningful Perturbation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[13]  Kate Saenko,et al.  RISE: Randomized Input Sampling for Explanation of Black-box Models , 2018, BMVC.

[14]  Bastian Leibe,et al.  Superpixels: An evaluation of the state-of-the-art , 2016, Comput. Vis. Image Underst..

[15]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Owen Carmichael,et al.  Standardization of analysis sets for reporting results from ADNI MRI data , 2013, Alzheimer's & Dementia.

[17]  L. Mosconi,et al.  Brain glucose metabolism in the early and specific diagnosis of Alzheimer’s disease , 2005, European Journal of Nuclear Medicine and Molecular Imaging.

[18]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[19]  Pascal Vincent,et al.  Visualizing Higher-Layer Features of a Deep Network , 2009 .

[20]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[21]  Alexander Binder,et al.  Evaluating the Visualization of What a Deep Neural Network Has Learned , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[23]  Jian Sun,et al.  Saliency Optimization from Robust Background Detection , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[25]  Seth Flaxman,et al.  European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" , 2016, AI Mag..

[26]  Andy C. H. Lee,et al.  Differentiating the Roles of the Hippocampus and Perirhinal Cortex in Processes beyond Long-Term Declarative Memory: A Double Dissociation in Dementia , 2006, The Journal of Neuroscience.

[27]  Shane T. Barratt.  InterpNET: Neural Introspection for Interpretable Deep Learning , 2017, ArXiv.

[28]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.