← Search

Omer Belhasin

2 accepted papers

2026

Advancing Image Classification with Discrete Diffusion Classification Modeling

CVPR 2026

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

Cited by 0SourcecodeScholar
2022

TransBoost: Improving the Best ImageNet Performance using Deep Transduction

NeurIPS 2022accept

This paper deals with deep transductive learning, and proposes TransBoost as a procedure for fine-tuning any deep neural model to improve its performance on any (unlabeled) test set provided at training time. TransBoost is inspired by a large margin principle and is efficient and simple to use. Our…