Weight Group-wise Post-Training Quantization for Medical Foundation Model

arXiv:2604.07674v1 Announce Type: new Abstract: Foundation models have achieved remarkable results in medical image analysis. However, its large network architecture and high computational complexity significantly impact inference speed, limiting its application on terminal medical devices. Quantization, a technique that compresses models into low-bit versions, is a solution to this challenge. In this paper, we propose a post-training quantization algorithm, Permutation-COMQ. It eliminates the need for backpropagation by using simple dot products and rounding operations, thereby removing hyperparameter tuning and simplifying the process. Additionally, we introduce a weight-aware strategy that reorders the weight within each layer to address the accuracy degradation induced by channel-wise scaling during quantization, while preserving channel structure. Experiments demonstrate that our method achieves the best results in 2-bit, 4-bit, and 8-bit quantization.

Related

• Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
• When Fine-Tuning Changes the Evidence: Architecture-Dependent Semantic Drift in Chest X-Ray Explanations
• Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow
• Hierarchical Feature Learning for Medical Point Clouds via State Space Model
• Flemme: A Flexible and Modular Learning Platform for Medical Images

Source: arXiv cs.CV | 2026-04-10