Example-based explanations with adversarial attacks for respiratory sound analysis
- 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 showRespiratory 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.…
Author: | Yi Chang, Zhao RenORCiD, Thanh Tam Nguyen, Wolfgang Nejdl, Björn W. SchullerORCiDGND |
---|---|
URN: | urn:nbn:de:bvb:384-opus4-992871 |
Frontdoor URL | https://opus.bibliothek.uni-augsburg.de/opus4/99287 |
Parent Title (English): | Interspeech 2022, Incheon, Korea, 18-22 September 2022 |
Publisher: | ISCA |
Place of publication: | Baixas |
Editor: | Hanseok Ko, John H. L. Hansen |
Type: | Conference Proceeding |
Language: | English |
Year of first Publication: | 2022 |
Publishing Institution: | Universität Augsburg |
Release Date: | 2022/11/15 |
First Page: | 4003 |
Last Page: | 4007 |
DOI: | https://doi.org/10.21437/interspeech.2022-11355 |
Institutes: | Fakultät für Angewandte Informatik |
Fakultät für Angewandte Informatik / Institut für Informatik | |
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Embedded Intelligence for Health Care and Wellbeing | |
Dewey Decimal Classification: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
Licence (German): | Deutsches Urheberrecht |