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


Hu Wang (Mohamed bin Zayed University of Artificial Intelligence), Ibrahim Almakky (Mohamed bin Zayed University of Artificial Intelligence), Congbo Ma (New York University), Numan Saeed (Mohamed bin Zayed University of Artificial Intelligence), Mohammad Yaqub (Mohamed bin Zayed University of Artificial Intelligence)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)

Abstract

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 is available at https://github.com/billhhh/In-Model-Merging.

Citation

@inproceedings{Wang_2025_BMVC,
author    = {Hu Wang and Ibrahim Almakky and Congbo Ma and Numan Saeed and Mohammad Yaqub},
title     = {In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_1015/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection