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

arXiv: https://arxiv.org/abs/2502.20516 · HTML: https://mlsanity.com/paper/2502.20516/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)
- [CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning](https://mlsanity.com/paper/1711.05225/) (2017)
- [Dataless Knowledge Fusion by Merging Weights of Language Models](https://mlsanity.com/paper/2212.09849/) (2022)
- [The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks](https://mlsanity.com/paper/2110.06296/) (2021)
- [ZipIt! Merging Models from Different Tasks without Training](https://mlsanity.com/paper/2305.03053/) (2023)
- [REPAIR: REnormalizing Permuted Activations for Interpolation Repair](https://mlsanity.com/paper/2211.08403/) (2022)
- [Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2405.00571/) (2024)
- [Learning to diagnose from scratch by exploiting dependencies among labels](https://mlsanity.com/paper/1710.10501/) (2017)
- [Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks](https://mlsanity.com/paper/1803.04565/) (2018)
- [Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographs](https://mlsanity.com/paper/1807.07532/) (2018)
- [Multi-label Thoracic Disease Image Classification with Cross-Attention Networks](https://mlsanity.com/paper/2007.10859/) (2020)
- [FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation](https://mlsanity.com/paper/2307.10507/) (2023)
- [Rethinking Weight-Averaged Model-merging](https://mlsanity.com/paper/2411.09263/) (2024)
- [MedMerge: Merging Models for Effective Transfer Learning to Medical Imaging Tasks](https://mlsanity.com/paper/2403.11646/) (2024)
- [Learning Physics-Inspired Regularization for Medical Image Registration with Hypernetworks](https://mlsanity.com/paper/2311.08239/) (2023)

## Built on by (most cited first, 1 of 1)

- [T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis](https://mlsanity.com/paper/2510.27265/) (2025)

## Abstract (arXiv)

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.