Scholarlink

<p>This work introduces SqueezeViT (Squeeze Vision Transformers), a compact yet effective architecture based on Vision Transformers (ViT) designed for chest X-ray (CXR) image classification. In contrast to traditional ViT architectures, which are computationally demanding, SqueezeViT employs a novel squeezing procedure that effectively lowers token dimensions without compromising important visual components, leading to expedited inference and decreased memory consumption. The designed model is tested for two commonly used public datasets, NIH Chest X-ray and CheXpert, providing a diverse range of thoracic pathologies. SqueezeViT reduces the number of parameters by 43.2% compared to the baseline MobileViT<sup><CitationRef CitationID="CR1">1</CitationRef></sup>, and up to 95.4% compared to other state-of-the-art (SOTA) models. The suggested model offers up to 16.5% improvement in the area under the receiver operating characteristic curve (AUROC) compared to SOTA models, and it is, in general, superior to the baseline and effective convolutional neural networks CNNs<sup><CitationRef CitationID="CR2">2</CitationRef></sup> in numerous tasks. Such developments make the proposed SqueezeViT approach an attractive option for a wide variety of applications. The findings indicate that SqueezeViT outperforms the current SOTA classifiers while maintaining a lightweight model architecture. In turn, such results emphasize the possibilities of using SqueezeViT in real clinical environment, where the amount of computational resources can be constrained.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Efficient SqueezeViT: A lightweight vision transformer framework for chest X-ray image classification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月9日

查看全文
  • Abhinav Maurya,
  • Ashish Lohia,
  • Chirag,
  • Jyoti Yadav,
  • Bharti Panjwani,
  • Vijay Mohan

摘要

This work introduces SqueezeViT (Squeeze Vision Transformers), a compact yet effective architecture based on Vision Transformers (ViT) designed for chest X-ray (CXR) image classification. In contrast to traditional ViT architectures, which are computationally demanding, SqueezeViT employs a novel squeezing procedure that effectively lowers token dimensions without compromising important visual components, leading to expedited inference and decreased memory consumption. The designed model is tested for two commonly used public datasets, NIH Chest X-ray and CheXpert, providing a diverse range of thoracic pathologies. SqueezeViT reduces the number of parameters by 43.2% compared to the baseline MobileViT1, and up to 95.4% compared to other state-of-the-art (SOTA) models. The suggested model offers up to 16.5% improvement in the area under the receiver operating characteristic curve (AUROC) compared to SOTA models, and it is, in general, superior to the baseline and effective convolutional neural networks CNNs2 in numerous tasks. Such developments make the proposed SqueezeViT approach an attractive option for a wide variety of applications. The findings indicate that SqueezeViT outperforms the current SOTA classifiers while maintaining a lightweight model architecture. In turn, such results emphasize the possibilities of using SqueezeViT in real clinical environment, where the amount of computational resources can be constrained.