Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models

Abstract

Gaining insight into how deep convolutional neural network models perform image classification and how to explain their outputs have been a concern to computer vision researchers and decision makers. These deep models are often referred to as black box due to low comprehension of their internal workings. As an effort to developing explainable deep learning models, several methods have been proposed such as finding gradients of class output with respect to input image (sensitivity maps), class activation map (CAM), and Gradient based Class Activation Maps (Grad-CAM). These methods under perform when localizing multiple occurrences of the same class and do not work for all CNNs. In addition, Grad-CAM does not capture the entire object in completeness when used on single object images, this affect performance on recognition tasks. With the intention to create an enhanced visual explanation in terms of visual sharpness, object localization and explaining multiple occurrences of objects in a single image, we present Smooth Grad-CAM++ \footnote{Simple demo: http://35.238.22.135:5000/}, a technique that combines methods from two other recent techniques---SMOOTHGRAD and Grad-CAM++. Our Smooth Grad-CAM++ technique provides the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance at the inference level (model prediction process). After experimenting with few images, Smooth Grad-CAM++ produced more visually sharp maps with better localization of objects in the given input images when compared with other methods.

Accepted in the Intelligent Systems Conference 2019

References in corpus (9)

• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Axiomatic Attribution for Deep Networks
• Striving for Simplicity: The All Convolutional Net
• Learning Important Features Through Propagating Activation Differences
• Understanding Neural Networks Through Deep Visualization
• SmoothGrad: removing noise by adding noise
• Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
• A New Method to Visualize Deep Neural Networks
• Subset Scanning Over Neural Network Activations

Cited by in corpus (16)

• Explanations in Autonomous Driving: A Survey
• Review: Deep Learning in Electron Microscopy
• Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
• Efficient Saliency Maps for Explainable AI
• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application
• IS-CAM: Integrated Score-CAM for axiomatic-based explanations
• ImageAssist: Tools for Enhancing Touchscreen-Based Image Exploration Systems for Blind and Low Vision Users
• Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation
• Local Black-box Adversarial Attacks: A Query Efficient Approach
• SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost
• On The Coherence of Quantitative Evaluation of Visual Explanations
• Interpreting Interpretations: Organizing Attribution Methods by Criteria
• Weakly Supervised Minirhizotron Image Segmentation with MIL-CAM
• Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring
• SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods