Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis
23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022
; 2022-September:4003-4007, 2022.
Article
in English
| Scopus | ID: covidwho-2091315
ABSTRACT
Respiratory sound classification is an important tool for remote screening of respiratory-related diseases such as pneumonia, asthma, and COVID-19. To facilitate the interpretability of classification results, especially ones based on deep learning, many explanation methods have been proposed using prototypes. However, existing explanation techniques often assume that the data is non-biased and the prediction results can be explained by a set of prototypical examples. In this work, we develop a unified example-based explanation method for selecting both representative data (prototypes) and outliers (criticisms). In particular, we propose a novel application of adversarial attacks to generate an explanation spectrum of data instances via an iterative fast gradient sign method. Such unified explanation can avoid over-generalisation and bias by allowing human experts to assess the model mistakes case by case. We performed a wide range of quantitative and qualitative evaluations to show that our approach generates effective and understandable explanation and is robust with many deep learning models. Copyright © 2022 ISCA.
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS