Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classification

• URL: http://arxiv.org/abs/2501.00064v1
• Date: Sun, 29 Dec 2024 12:44:13 GMT
• Title: Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classification
• Authors: Shijia Ge, Weixiang Zhang, Shuzhao Xie, Baixu Yan, Zhi Wang,
• Abstract summary: Lungmix is a novel data augmentation technique inspired by Mixup. It generates augmented data by blending waveforms using loudness and random masks while interpolating labels based on their semantic meaning. It boosts the 4-class classification score by up to 3.55%, achieving performance comparable to models trained directly on the target dataset.
• Score: 3.879898053132466
• License:
• Abstract: Respiratory sound classification plays a pivotal role in diagnosing respiratory diseases. While deep learning models have shown success with various respiratory sound datasets, our experiments indicate that models trained on one dataset often fail to generalize effectively to others, mainly due to data collection and annotation \emph{inconsistencies}. To address this limitation, we introduce \emph{Lungmix}, a novel data augmentation technique inspired by Mixup. Lungmix generates augmented data by blending waveforms using loudness and random masks while interpolating labels based on their semantic meaning, helping the model learn more generalized representations. Comprehensive evaluations across three datasets, namely ICBHI, SPR, and HF, demonstrate that Lungmix significantly enhances model generalization to unseen data. In particular, Lungmix boosts the 4-class classification score by up to 3.55\%, achieving performance comparable to models trained directly on the target dataset.

Related papers

• CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive Learning [9.215130010602634]
  Auscultation plays a pivotal role in early respiratory and pulmonary disease diagnosis. Existing state-of-the-art models suffer from excessive parameter size, impeding deployment on resource-constrained mobile platforms. We propose a framework based on an improved deep clustering and contrastive learning. We deploy the network on Android devices, showcasing a comprehensive intelligent respiratory sound auscultation system.
  arXiv  Detail & Related papers  (2025-02-02T09:56:47Z)
• RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health Prediction [20.974460332254544]
  RespLLM is a novel framework that unifies text and audio representations for respiratory health prediction. Our work lays the foundation for multimodal models that can perceive, listen, and understand heterogeneous data.
  arXiv  Detail & Related papers  (2024-10-07T17:06:11Z)
• Learning with Noisy Foundation Models [95.50968225050012]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets. We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification [18.56326840619165]
  We introduce a novel and effective Patch-Mix Contrastive Learning to distinguish the mixed representations in the latent space. Our method achieves state-of-the-art performance on the ICBHI dataset, outperforming the prior leading score by an improvement of 4.08%.
  arXiv  Detail & Related papers  (2023-05-23T13:04:07Z)
• Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks [75.42002070547267]
  We propose a self evolution learning (SE) based mixup approach for data augmentation in text classification. We introduce a novel instance specific label smoothing approach, which linearly interpolates the model's output and one hot labels of the original samples to generate new soft for label mixing up.
  arXiv  Detail & Related papers  (2023-05-22T23:43:23Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data [93.06336507035486]
  Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
  arXiv  Detail & Related papers  (2022-10-27T02:55:15Z)
• DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification [56.817386699291305]
  This paper proposes a simple yet effective data augmentation approach termed DoubleMix. DoubleMix first generates several perturbed samples for each training data. It then uses the perturbed data and original data to carry out a two-step in the hidden space of neural models.
  arXiv  Detail & Related papers  (2022-09-12T15:01:04Z)
• Lung Sound Classification Using Co-tuning and Stochastic Normalization [26.399917342840265]
  The knowledge of the pre-trained model is transferred by using vanilla fine-tuning, co-tuning, normalization and the combination of the co-tuning and normalization techniques. Our proposed systems mostly outperform all state-of-the-art lung sound classification systems for the adventitious lung sounds and respiratory diseases of both datasets.
  arXiv  Detail & Related papers  (2021-08-04T12:16:02Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)
• CNN-MoE based framework for classification of respiratory anomalies and lung disease detection [33.45087488971683]
  This paper presents and explores a robust deep learning framework for auscultation analysis. It aims to classify anomalies in respiratory cycles and detect disease, from respiratory sound recordings.
  arXiv  Detail & Related papers  (2020-04-04T21:45:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.