# Geometry-Aware Optimization for Respiratory Sound Classification: Enhancing Sensitivity with SAM-Optimized Audio Spectrogram Transformers

arXiv: https://arxiv.org/abs/2512.22564 · HTML: https://mlsanity.com/paper/2512.22564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [RespireNet: A Deep Neural Network for Accurately Detecting Abnormal Lung Sounds in Limited Data Setting](https://mlsanity.com/paper/2011.00196/) (2020)
- [Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification](https://mlsanity.com/paper/2305.14032/) (2023)
- [Masked Modeling Duo: Towards a Universal Audio Pre-training Framework](https://mlsanity.com/paper/2404.06095/) (2024)
- [Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification](https://mlsanity.com/paper/2312.09603/) (2023)
- [Lung Sound Classification Using Co-tuning and Stochastic Normalization](https://mlsanity.com/paper/2108.01991/) (2021)
- [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)
- [Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance](https://mlsanity.com/paper/2311.06480/) (2023)
- [Multi-View Spectrogram Transformer for Respiratory Sound Classification](https://mlsanity.com/paper/2311.09655/) (2023)
- [Adaptive Differential Denoising for Respiratory Sounds Classification](https://mlsanity.com/paper/2506.02505/) (2025)

## Abstract (arXiv)

Respiratory sound classification is hindered by the limited size, high noise levels, and severe class imbalance of benchmark datasets like ICBHI 2017. While Transformer-based models offer powerful feature extraction capabilities, they are prone to overfitting and often converge to sharp minima in the loss landscape when trained on such constrained medical data. To address this, we introduce a framework that enhances the Audio Spectrogram Transformer (AST) using Sharpness-Aware Minimization (SAM). Instead of merely minimizing the training loss, our approach optimizes the geometry of the loss surface, guiding the model toward flatter minima that generalize better to unseen patients. We also implement a weighted sampling strategy to handle class imbalance effectively. Our method achieves a state-of-the-art score of 68.10% on the ICBHI 2017 dataset, outperforming existing CNN and hybrid baselines. More importantly, it reaches a sensitivity of 68.31%, a crucial improvement for reliable clinical screening. Further analysis using t-SNE and attention maps confirms that the model learns robust, discriminative features rather than memorizing background noise.