ICBHI AST SAM

--- base_model: - MIT/ast-finetuned-audioset-10-10-0.4593 language: - en license: mit pipeline_tag: audio-classification tags: - audio-classification - medical --- # Geometry-Aware Optimization for Respiratory Sound Classification (AST + SAM) This repository contains the model weights for the paper "[Geometry-Aware Optimization for Respiratory Sound Classification: Enhancing Sensitivity with SAM-Optimized Audio Spectrogram Transformers](https://huggingface.co/papers/2512.22564)". ## Description Respiratory sound classification is often hindered by limited datasets and class imbalance. This framework enhances the **Audio Spectrogram Transformer (AST)** by using **Sharpness-Aware Minimization (SAM)**. Instead of merely minimizing training loss, this approach optimizes the geometry of the loss surface, guiding the model toward flatter minima that generalize better to unseen patients. The method specifically aims to improve sensitivity, a crucial metric for reliable clinical screening. ## Key Results (ICBHI 2017 Official Split) | Metric | Score | | :--- | :--- | | **Sensitivity (Se)** | **68.31%** | | **Specificity (Sp)** | **67.89%** | | **ICBHI Score** | **68.10%** | ## Links - **GitHub Repository**: [Atakanisik/ICBHI-AST-SAM](https://github.com/Atakanisik/ICBHI-AST-SAM) - **Paper**: [arXiv:2512.22564](https://arxiv.org/abs/2512.22564) ## Citation If you use this model or code in your research, please cite: ```bibtex @article{isik2025geometry, title={Geometry-Aware Optimization for Respiratory Sound Classification: Enhancing Sensitivity with SAM-Optimized Audio Spectrogram Transformers}, author={I\c{s}{\i}k, Atakan and Vulga I\c{s}{\i}k, Selin and I\c{s}{\i}k, Ahmet Feridun and Taylan, Mah\c{s}uk}, journal={arXiv preprint arXiv:2512.22564}, year={2025} } ```

Source context: 0 downloads · 0 likes · Pipeline audio-classification · Repo Atakanisik/ICBHI-AST-SAM