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

TL;DR

Smooth Grad-CAM++ is a novel visualization method that enhances deep CNN interpretability by producing sharper, more localized, and comprehensive visual explanations of model predictions, especially for multiple object instances.

Contribution

It combines SmoothGrad and Grad-CAM++ techniques to improve visualization sharpness, object localization, and multi-object explanation capabilities during inference.

Findings

Produces more visually sharp activation maps

Improves object localization accuracy

Effectively visualizes multiple object occurrences

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.