In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Hu, Almakky, Ibrahim, Ma, Congbo, Saeed, Numan, Yaqub, Mohammad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916739124559872
author Wang, Hu
Almakky, Ibrahim
Ma, Congbo
Saeed, Numan
Yaqub, Mohammad
author_facet Wang, Hu
Almakky, Ibrahim
Ma, Congbo
Saeed, Numan
Yaqub, Mohammad
contents Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the merging process can occur within one model and enhance the model's robustness, which is particularly critical in the medical image domain. In the paper, we are the first to propose in-model merging (InMerge), a novel approach that enhances the model's robustness by selectively merging similar convolutional kernels in the deep layers of a single convolutional neural network (CNN) during the training process for classification. We also analytically reveal important characteristics that affect how in-model merging should be performed, serving as an insightful reference for the community. We demonstrate the feasibility and effectiveness of this technique for different CNN architectures on 4 prevalent datasets. The proposed InMerge-trained model surpasses the typically-trained model by a substantial margin. The code will be made public.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models
Wang, Hu
Almakky, Ibrahim
Ma, Congbo
Saeed, Numan
Yaqub, Mohammad
Computer Vision and Pattern Recognition
Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the merging process can occur within one model and enhance the model's robustness, which is particularly critical in the medical image domain. In the paper, we are the first to propose in-model merging (InMerge), a novel approach that enhances the model's robustness by selectively merging similar convolutional kernels in the deep layers of a single convolutional neural network (CNN) during the training process for classification. We also analytically reveal important characteristics that affect how in-model merging should be performed, serving as an insightful reference for the community. We demonstrate the feasibility and effectiveness of this technique for different CNN architectures on 4 prevalent datasets. The proposed InMerge-trained model surpasses the typically-trained model by a substantial margin. The code will be made public.
title In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.20516