Explainable Deep Classification Models for Domain Generalization

03/13/2020
by   Andrea Zunino, et al.
21

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible accuracy degradation. Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision. This is represented in the form of a saliency map conveying how much each pixel contributed to the network's decision. Our training strategy enforces a periodic saliency-based feedback to encourage the model to focus on the image regions that directly correspond to the ground-truth object. We quantify explainability using an automated metric, and using human judgement. We propose explainability as a means for bridging the visual-semantic gap between different domains where model explanations are used as a means of disentagling domain specific information from otherwise relevant features. We demonstrate that this leads to improved generalization to new domains without hindering performance on the original domain.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 7

page 8

research
06/04/2020

SIDU: Similarity Difference and Uniqueness Method for Explainable AI

A new brand of technical artificial intelligence ( Explainable AI ) rese...
research
04/05/2021

Explainability-aided Domain Generalization for Image Classification

Traditionally, for most machine learning settings, gaining some degree o...
research
09/21/2020

Survey of explainable machine learning with visual and granular methods beyond quasi-explanations

This paper surveys visual methods of explainability of Machine Learning ...
research
09/22/2020

What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoors

EXplainable AI (XAI) methods have been proposed to interpret how a deep ...
research
05/29/2023

Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition

Explainable AI (XAI) techniques have been widely used to help explain an...
research
08/06/2020

Improving Explainability of Image Classification in Scenarios with Class Overlap: Application to COVID-19 and Pneumonia

Trust in predictions made by machine learning models is increased if the...
research
03/20/2022

Explainable Misinformation Detection Across Multiple Social Media Platforms

In this work, the integration of two machine learning approaches, namely...

Please sign up or login with your details

Forgot password? Click here to reset