CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging

• URL: http://arxiv.org/abs/2510.27442v1
• Date: Fri, 31 Oct 2025 12:49:13 GMT
• Title: CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
• Abstract summary: CoMViT is a compact and generalizable Vision Transformer architecture optimized for resource-constrained medical image analysis.<n>It achieves robust performance across twelve MedMNIST datasets while maintaining a lightweight design with only 4.5M parameters.
• Score: 0.3683202928838613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA [55.12170695219291]
  MedFG-VQA is a lightweight framework that augments DCT-based low-frequency features and employs graph-enhanced cross-attention for effective visual-textual alignment.<n>To address data scarcity, we construct SynMed-VQA, a large-scale synthetic dataset comprising over 2 million question-answer pairs across 9 imaging modalities and 10 major organs.
  arXiv  Detail & Related papers  (2026-08-27T09:16:14Z)
• MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models [59.180043227905294]
  We propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework for efficient 3D medical image understanding.<n>We show that MedPruner enables models such as MedGemma to maintain or even exceed their original performance while retaining fewer than 5% of visual tokens.
  arXiv  Detail & Related papers  (2026-03-12T07:37:00Z)
• Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging [0.7865560760233441]
  We introduce a novel PEFT framework that employs depth-aware scaling to increase adapter capacity from shallow to deep transformer layers.<n>Our method integrates lightweight bottleneck modules within CLIPSeg's vision and text encoders, with adapter dimensions dynamically scaled based on layer depth and semantic relevance.<n>Our approach establishes a new paradigm for efficient medical VLSM fine-tuning, enabling deployment in resource-constrained clinical environments.
  arXiv  Detail & Related papers  (2025-12-15T19:40:15Z)
• MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation [63.38824041721275]
  Low-resolution (LR) medical videos present unique challenges for video super-resolution (VSR) models.<n>We propose MedVSR, a tailored framework for medical VSR.<n>We show that MedVSR significantly outperforms existing VSR models in reconstruction performance and efficiency.
  arXiv  Detail & Related papers  (2025-09-25T14:56:59Z)
• Systematic Integration of Attention Modules into CNNs for Accurate and Generalizable Medical Image Diagnosis [7.082043294630761]
  We integrate attention mechanisms into five widely adopted CNN architectures.<n>Each baseline model is augmented with either a Squeeze and Excitation block or a hybrid Convolutional Block Attention Module.<n>We show that attention augmented CNNs consistently outperform baseline architectures across all metrics.
  arXiv  Detail & Related papers  (2025-09-02T05:45:27Z)
• ClipGS: Clippable Gaussian Splatting for Interactive Cinematic Visualization of Volumetric Medical Data [51.095474325541794]
  We introduce ClipGS, an innovative Gaussian splatting framework with the clipping plane supported, for interactive cinematic visualization of medical data.<n>We validate our method on five volumetric medical data, and reach an average 36.635 PSNR rendering quality with 156 FPS and 16.1 MB model size.
  arXiv  Detail & Related papers  (2025-07-09T08:24:28Z)
• CNN and ViT Efficiency Study on Tiny ImageNet and DermaMNIST Datasets [0.0]
  We introduce a fine-tuning strategy applied to four Vision Transformer variants (Tiny, Small, Base, Large) on DermatologyMNIST and TinyImageNet.<n>We demonstrate that appropriately fine-tuned Vision Transformers can match or exceed the baseline's performance, achieve faster inference, and operate with fewer parameters.
  arXiv  Detail & Related papers  (2025-05-13T06:17:18Z)
• Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention [9.359961857595144]
  We introduce the Medical Vision Transformer (MedViTV2) for generalized medical image classification.<n>MedViTV2 is 44% more computationally efficient than the previous version.<n>It significantly enhances accuracy, achieving improvements of 4.6% on MedMNIST, 5.8% on NonMNIST, and 13.4% on the MedMNIST-C benchmark.
  arXiv  Detail & Related papers  (2025-02-19T13:05:50Z)
• RWKV-UNet: Improving UNet with Long-Range Cooperation for Effective Medical Image Segmentation [70.79072961974141]
  We propose RWKV-UNet, a novel model that integrates the RWKV structure into the U-Net architecture.<n>This integration enhances the model's ability to capture long-range dependencies and to improve contextual understanding.<n> Experiments on 11 benchmark datasets show that the RWKV-UNet achieves state-of-the-art performance on various types of medical image segmentation tasks.
  arXiv  Detail & Related papers  (2025-01-14T22:03:00Z)
• Rethinking model prototyping through the MedMNIST+ dataset collection [0.11999555634662634]
  This work introduces a comprehensive benchmark for the MedMNIST+ dataset collection.<n>We reassess commonly used Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures across distinct medical datasets.<n>Our findings suggest that computationally efficient training schemes and modern foundation models offer viable alternatives to costly end-to-end training.
  arXiv  Detail & Related papers  (2024-04-24T10:19:25Z)
• AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images [53.29794593104923]
  We present a novel concept of shared-context processing for whole slide histopathology images. AMIGO uses the celluar graph within the tissue to provide a single representation for a patient. We show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data.
  arXiv  Detail & Related papers  (2023-03-01T23:37:45Z)
• GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer [76.2625311630021]
  Vision transformers (ViTs) have shown very impressive empirical performance in various computer vision tasks. To mitigate this challenging problem, structured pruning is a promising solution to compress model size and enable practical efficiency. We propose GOHSP, a unified framework of Graph and Optimization-based Structured Pruning for ViT models.
  arXiv  Detail & Related papers  (2023-01-13T00:40:24Z)
• Medical Transformer: Gated Axial-Attention for Medical Image Segmentation [73.98974074534497]
  We study the feasibility of using Transformer-based network architectures for medical image segmentation tasks. We propose a Gated Axial-Attention model which extends the existing architectures by introducing an additional control mechanism in the self-attention module. To train the model effectively on medical images, we propose a Local-Global training strategy (LoGo) which further improves the performance.
  arXiv  Detail & Related papers  (2021-02-21T18:35:14Z)

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.