Saved in:
Bibliographic Details
Main Authors: Ukita, Kosuke, Xiaolong, Ye, Okita, Tsuyoshi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.06890
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912370078515200
author Ukita, Kosuke
Xiaolong, Ye
Okita, Tsuyoshi
author_facet Ukita, Kosuke
Xiaolong, Ye
Okita, Tsuyoshi
contents In this paper, we propose a diffusion model that integrates a representation-conditioning mechanism, where the representations derived from a Vision Transformer (ViT) are used to condition the internal process of a Transformer-based diffusion model. This approach enables representation-conditioned data generation, addressing the challenge of requiring large-scale labeled datasets by leveraging self-supervised learning on unlabeled data. We evaluate our method through a zero-shot classification task for hematoma detection in brain imaging. Compared to the strong contrastive learning baseline, DINOv2, our method achieves a notable improvement of +6.15% in accuracy and +13.60% in F1-score, demonstrating its effectiveness in image classification.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06890
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Image Classification Using a Diffusion Model as a Pre-Training Model
Ukita, Kosuke
Xiaolong, Ye
Okita, Tsuyoshi
Machine Learning
Computer Vision and Pattern Recognition
Image and Video Processing
In this paper, we propose a diffusion model that integrates a representation-conditioning mechanism, where the representations derived from a Vision Transformer (ViT) are used to condition the internal process of a Transformer-based diffusion model. This approach enables representation-conditioned data generation, addressing the challenge of requiring large-scale labeled datasets by leveraging self-supervised learning on unlabeled data. We evaluate our method through a zero-shot classification task for hematoma detection in brain imaging. Compared to the strong contrastive learning baseline, DINOv2, our method achieves a notable improvement of +6.15% in accuracy and +13.60% in F1-score, demonstrating its effectiveness in image classification.
title Image Classification Using a Diffusion Model as a Pre-Training Model
topic Machine Learning
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2505.06890