轻量版视觉Transformer，专为小样本医学图像分类优化。
CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
- 用卷积分块+动态温度等设计，提升效率与泛化能力。
- 12个医学数据集上表现媲美甚至超越更大模型，参数仅450万。
- 适合资源受限的临床场景，且注意力区域符合医学常识。
视觉变压器（ViTs）在医学影像中展现出强大潜力，但其高计算成本和小数据集下过拟合问题限制了实际应用。本文提出CoMViT，一种专为资源受限的医学图像分析优化的紧凑且可泛化的视觉变压器架构。CoMViT融合卷积分词器、对角掩码、动态温度缩放及基于池化的序列聚合机制，在十二个MedMNIST数据集上实现稳健性能，参数量仅为约450万，相比更深的CNN和ViT模型，参数减少达5-20倍，同时保持或超越其准确率。定性Grad-CAM分析显示，尽管模型轻量，其注意力仍持续聚焦于临床相关区域。结果表明，通过合理设计，可构建高效且可解释的视觉变压器，适用于低资源医学影像场景。
原文摘要 · Abstract (English)
Vision Transformers (ViTs) have demonstrated strong potential in medical imaging; however, their high computational demands and tendency to overfit on small datasets limit their applicability in real-world clinical scenarios. In this paper, we present CoMViT, a compact and generalizable Vision Transformer architecture optimized for resource-constrained medical image analysis. CoMViT integrates a convolutional tokenizer, diagonal masking, dynamic temperature scaling, and pooling-based sequence aggregation to improve performance and generalization. Through systematic architectural optimization, CoMViT achieves robust performance across twelve MedMNIST datasets while maintaining a lightweight design with only ~4.5M parameters. It matches or outperforms deeper CNN and ViT variants, offering up to 5-20x parameter reduction without sacrificing accuracy. Qualitative Grad-CAM analyses show that CoMViT consistently attends to clinically relevant regions despite its compact size. These results highlight the potential of principled ViT redesign for developing efficient and interpretable models in low-resource medical imaging settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。