Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tsutsumi, Ayaka, Li, Guang, Togo, Ren, Ogawa, Takahiro, Kondo, Satoshi, Haseyama, Miki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915641350422528
author Tsutsumi, Ayaka
Li, Guang
Togo, Ren
Ogawa, Takahiro
Kondo, Satoshi
Haseyama, Miki
author_facet Tsutsumi, Ayaka
Li, Guang
Togo, Ren
Ogawa, Takahiro
Kondo, Satoshi
Haseyama, Miki
contents We propose a novel medical image classification method that integrates dual-model weight selection with self-knowledge distillation (SKD). In real-world medical settings, deploying large-scale models is often limited by computational resource constraints, which pose significant challenges for their practical implementation. Thus, developing lightweight models that achieve comparable performance to large-scale models while maintaining computational efficiency is crucial. To address this, we employ a dual-model weight selection strategy that initializes two lightweight models with weights derived from a large pretrained model, enabling effective knowledge transfer. Next, SKD is applied to these selected models, allowing the use of a broad range of initial weight configurations without imposing additional excessive computational cost, followed by fine-tuning for the target classification tasks. By combining dual-model weight selection with self-knowledge distillation, our method overcomes the limitations of conventional approaches, which often fail to retain critical information in compact models. Extensive experiments on publicly available datasets-chest X-ray images, lung computed tomography scans, and brain magnetic resonance imaging scans-demonstrate the superior performance and robustness of our approach compared to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20461
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classification
Tsutsumi, Ayaka
Li, Guang
Togo, Ren
Ogawa, Takahiro
Kondo, Satoshi
Haseyama, Miki
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
We propose a novel medical image classification method that integrates dual-model weight selection with self-knowledge distillation (SKD). In real-world medical settings, deploying large-scale models is often limited by computational resource constraints, which pose significant challenges for their practical implementation. Thus, developing lightweight models that achieve comparable performance to large-scale models while maintaining computational efficiency is crucial. To address this, we employ a dual-model weight selection strategy that initializes two lightweight models with weights derived from a large pretrained model, enabling effective knowledge transfer. Next, SKD is applied to these selected models, allowing the use of a broad range of initial weight configurations without imposing additional excessive computational cost, followed by fine-tuning for the target classification tasks. By combining dual-model weight selection with self-knowledge distillation, our method overcomes the limitations of conventional approaches, which often fail to retain critical information in compact models. Extensive experiments on publicly available datasets-chest X-ray images, lung computed tomography scans, and brain magnetic resonance imaging scans-demonstrate the superior performance and robustness of our approach compared to existing methods.
title Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.20461