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

Abstract

We present Smooth Grad-CAM++, a technique which combines two recent techniques: SMOOTHGRAD and Grad-CAM++. Smooth Grad-CAM++ has the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance. We experimented with few images, and we discovered that Smooth Grad-CAM++ produced more visually sharp maps with larger number of salient pixels highlighted in the given input images when compared with other methods. Smooth Grad-CAM++ will give insight into what our deep CNN models (including models trained on medical scan or imagery) learn. Hence informing decisions on creating a representative training set.

Presented at NeurIPS 2019 Workshop on Machine Learning for the Developing World. arXiv admin note: substantial text overlap with arXiv:1908.01224

References in corpus (6)

• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Axiomatic Attribution for Deep Networks
• Learning Important Features Through Propagating Activation Differences
• SmoothGrad: removing noise by adding noise
• A New Method to Visualize Deep Neural Networks
• Subset Scanning Over Neural Network Activations