Improving Deep Neural Network Classification Confidence using Heatmap-based eXplainable AI

12/30/2021
by   Erico Tjoa, et al.
0

This paper quantifies the quality of heatmap-based eXplainable AI methods w.r.t image classification problem. Here, a heatmap is considered desirable if it improves the probability of predicting the correct classes. Different XAI heatmap-based methods are empirically shown to improve classification confidence to different extents depending on the datasets, e.g. Saliency works best on ImageNet and Deconvolution on ChestX-Ray Pneumonia dataset. The novelty includes a new gap distribution that shows a stark difference between correct and wrong predictions. Finally, the generative augmentative explanation is introduced, a method to generate heatmaps maps capable of improving predictive confidence to a high level.

READ FULL TEXT
research
05/05/2023

Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models

We examined whether embedding human attention knowledge into saliency-ba...
research
07/31/2019

Competing Ratio Loss for Discriminative Multi-class Image Classification

The development of deep convolutional neural network architecture is cri...
research
10/19/2020

Failure Prediction by Confidence Estimation of Uncertainty-Aware Dirichlet Networks

Reliably assessing model confidence in deep learning and predicting erro...
research
06/16/2021

Explainable AI for Natural Adversarial Images

Adversarial images highlight how vulnerable modern image classifiers are...
research
11/28/2022

Predicting Football Match Outcomes with eXplainable Machine Learning and the Kelly Index

In this work, a machine learning approach is developed for predicting th...
research
07/09/2023

A Novel Explainable Artificial Intelligence Model in Image Classification problem

In recent years, artificial intelligence is increasingly being applied w...
research
03/21/2019

Empirical confidence estimates for classification by deep neural networks

How well can we estimate the probability that the classification, C(f(x)...

Please sign up or login with your details

Forgot password? Click here to reset