Score: 1

Advancing Image Classification with Discrete Diffusion Classification Modeling

Published: November 25, 2025 | arXiv ID: 2511.20263v1

By: Omer Belhasin , Shelly Golan , Ran El-Yaniv and more

Potential Business Impact:

Helps computers guess pictures better, even when unsure.

Business Areas:
Image Recognition Data and Analytics, Software

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 classification approaches typically train models to directly predict class labels from input images, but this might lead to suboptimal performance in such scenarios. To address this issue, we propose Discrete Diffusion Classification Modeling (DiDiCM), a novel framework that leverages a diffusion-based procedure to model the posterior distribution of class labels conditioned on the input image. DiDiCM supports diffusion-based predictions either on class probabilities or on discrete class labels, providing flexibility in computation and memory trade-offs. We conduct a comprehensive empirical study demonstrating the superior performance of DiDiCM over standard classifiers, showing that a few diffusion iterations achieve higher classification accuracy on the ImageNet dataset compared to baselines, with accuracy gains increasing as the task becomes more challenging. We release our code at https://github.com/omerb01/didicm .

Country of Origin
🇮🇱 Israel

Page Count
16 pages

Category
Computer Science:
CV and Pattern Recognition