Efficient Saliency Maps for Explainable AI

Abstract

We describe an explainable AI saliency map method for use with deep convolutional neural networks (CNN) that is much more efficient than popular fine-resolution gradient methods. It is also quantitatively similar or better in accuracy. Our technique works by measuring information at the end of each network scale which is then combined into a single saliency map. We describe how saliency measures can be made more efficient by exploiting Saliency Map Order Equivalence. We visualize individual scale/layer contributions by using a Layer Ordered Visualization of Information. This provides an interesting comparison of scale information contributions within the network not provided by other saliency map methods. Using our method instead of Guided Backprop, coarse-resolution class activation methods such as Grad-CAM and Grad-CAM++ seem to yield demonstrably superior results without sacrificing speed. This will make fine-resolution saliency methods feasible on resource limited platforms such as robots, cell phones, low-cost industrial devices, astronomy and satellite imagery.

arXiv commentIn submission to ECCV 2020

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Axiomatic Attribution for Deep Networks
• The information bottleneck method
• SmoothGrad: removing noise by adding noise
• Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models
• Training CNNs with Selective Allocation of Channels

Cited by in corpus (8)

• Acquisition of Chess Knowledge in AlphaZero
• Age-Net: An MRI-Based Iterative Framework for Brain Biological Age Estimation
• Model-agnostic explainable artificial intelligence for object detection in image data
• CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks
• An Automated Approach for Timely Diagnosis and Prognosis of Coronavirus Disease
• Explaining neural network predictions of material strength
• Investigating ADR mechanisms with knowledge graph mining and explainable AI
• Representaciones del aprendizaje reutilizando los gradientes de la retropropagacion