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

by   Daniel Omeiza, et al.

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++ [Simple demo:], 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.


page 5

page 6

page 8


A Step Towards Exposing Bias in Trained Deep Convolutional Neural Network Models

We present Smooth Grad-CAM++, a technique which combines two recent tech...

Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks

Over the last decade, Convolutional Neural Network (CNN) models have bee...

Recipro-CAM: Gradient-free reciprocal class activation map

Convolutional neural network (CNN) becomes one of the most popular and p...

SmoothGrad: removing noise by adding noise

Explaining the output of a deep network remains a challenge. In the case...

SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization

Deep Convolution Neural Networks are often referred to as black-box mode...

Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism

In this paper two new learning-based eXplainable AI (XAI) methods for de...

Grad-CAM++ is Equivalent to Grad-CAM With Positive Gradients

The Grad-CAM algorithm provides a way to identify what parts of an image...

Please sign up or login with your details

Forgot password? Click here to reset