Image Classification Using a Diffusion Model as a Pre-Training Model
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive Learningimage-classificationImage ClassificationmodelSelf-Supervised Learningzero-shot-classificationZero-Shot LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
From Graph Diffusion to Graph Classification
Generative models such as diffusion models have achieved remarkable success in state-of-the-art image and text tasks. Recently, score-based diffusion models have extended their success beyond image generation, showing co…
ClassificationGraph ClassificationImage GenerationAdvancing Image Classification with Discrete Diffusion Classification Modeling
Image classification is a well-studied task in computer vision, and yet it remains challenging under high-uncertainty conditions, such as when input images are corrupted or training data are limited. Conventional classif…
Image ClassificationEnhancing Fetal Plane Classification Accuracy with Data Augmentation Using Diffusion Models
Ultrasound imaging is widely used in medical diagnosis, especially for fetal health assessment. However, the availability of high-quality annotated ultrasound images is limited, which restricts the training of machine le…
Data AugmentationMedical DiagnosisDiffusion Models Beat GANs on Image Classification
While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a single pre-training stage to…
ClassificationDenoisingfeature selectionFine-Grained Image Classification+5Diffusion-Based Adaptation for Classification of Unknown Degraded Images
Classification of unknown degraded images is essential in practical applications since image-degraded models are usually unknown. Diffusion-based models provide enhanced performance for image enhancement and image restor…
ClassificationDomain GeneralizationImage EnhancementImage Restoration