# Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis

arXiv: https://arxiv.org/abs/2203.16141 · HTML: https://mlsanity.com/paper/2203.16141/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 35 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 10 of 10)

- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use](https://mlsanity.com/paper/1905.05134/) (2019)
- [Robust Classification with Convolutional Prototype Learning](https://mlsanity.com/paper/1805.03438/) (2018)
- [Interpretable and Steerable Sequence Learning via Prototypes](https://mlsanity.com/paper/1907.09728/) (2019)
- [Triplet-Center Loss for Multi-View 3D Object Retrieval](https://mlsanity.com/paper/1803.06189/) (2018)
- [Prototype Learning for Interpretable Respiratory Sound Analysis](https://mlsanity.com/paper/2110.03536/) (2021)
- [SAN-M: Memory Equipped Self-Attention for End-to-End Speech Recognition](https://mlsanity.com/paper/2006.01713/) (2020)
- [CAA-Net: Conditional Atrous CNNs with Attention for Explainable Device-robust Acoustic Scene Classification](https://mlsanity.com/paper/2011.09299/) (2020)
- [Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization](https://mlsanity.com/paper/2007.07689/) (2020)

## Built on by (most cited first, 13 of 13)

- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification](https://mlsanity.com/paper/2305.14032/) (2023)
- [Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification](https://mlsanity.com/paper/2312.09603/) (2023)
- [RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification](https://mlsanity.com/paper/2405.02996/) (2024)
- [BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification](https://mlsanity.com/paper/2406.06786/) (2024)
- [Model-Agnostic and Diverse Explanations for Streaming Rumour Graphs](https://mlsanity.com/paper/2207.08098/) (2022)
- [Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience](https://mlsanity.com/paper/2405.18040/) (2024)
- [A Comprehensive Survey on Heart Sound Analysis in the Deep Learning Era](https://mlsanity.com/paper/2301.09362/) (2023)
- [Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles](https://mlsanity.com/paper/2505.22027/) (2025)
- [CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive Learning](https://mlsanity.com/paper/2502.00734/) (2025)
- [Improving Deep Learning-based Respiratory Sound Analysis with Frequency Selection and Attention Mechanism](https://mlsanity.com/paper/2507.20052/) (2025)
- [Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis](https://mlsanity.com/paper/2602.15909/) (2026)
- [Meta-Ensemble Learning with Diverse Data Splits for Improved Respiratory Sound Classification](https://mlsanity.com/paper/2604.24096/) (2026)

## Abstract (arXiv)

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