Onur Can Koyun

According to our database, Onur Can Koyun authored at least 13 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

RamanFormerSSL: A self-supervised learning based transformer model for Raman mixture component quantification.

Onur Can Koyun, Reyhan Kevser Keser, Safa Onur Sahin, Damla Bulut, Mustafa Yorulmaz, Veysel Yücesoy, Behçet Ugur Töreyin

Neural Comput. Appl., May, 2026

Momentum Memory for Knowledge Distillation in Computational Pathology.

Yongxin Guo, Hao Lu, Onur Can Koyun, Zhengjie Zhu, Muhammet Fatih Demir, Metin Nafi Gürcan

CoRR, February, 2026

PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse.

Hao Lu, Onur Can Koyun, Yongxin Guo, Zhengjie Zhu, Abbas Alili, Metin Nafi Gürcan

CoRR, February, 2026

Beyond Stationarity: Rethinking Codebook Collapse in Vector Quantization.

Hao Lu, Onur Can Koyun, Yongxin Guo, Zhengjie Zhu, Abbas Alili, Metin Nafi Gürcan

CoRR, February, 2026

H&E to Oncotype DX: Predicting recurrence risk in HR+/HER2- breast cancer.

Onur Can Koyun, Yongxin Guo, Ziyu Su, Hao Lu, Mostafa Rezapour, Robert Wesolowski, Gary Tozbikian, M. Khalid Khan Niazi, Metin N. Gurcan

Expert Syst. Appl., 2026

Improving colorectal tumor bud segmentation with deformable multi-scale transformers.

Mesut Seker, Onur Can Koyun, Wei Chen, Wendy L. Frankel, M. Khalid Khan Niazi, Metin Nafi Gürcan

Biomed. Signal Process. Control., 2026

HalF&D: A Parameter Efficient Small Object Detection Approach.

Ahmet Nuri Yilmaz, Onur Can Koyun, Behçet Ugur Töreyin

Proceedings of the IEEE International Symposium on Circuits and Systems, 2026

2025

BPMambaMIL: A bio-inspired prototype-guided multiple instance learning for oncotype DX risk assessment in histopathology.

Yongxin Guo, Ziyu Su, Onur Can Koyun, Hao Lu, Robert Wesolowski, Gary Tozbikian, M. Khalid Khan Niazi, Metin N. Gurcan

Comput. Methods Programs Biomed., 2025

2024

Do deep neural networks utilize the weight space efficiently?

Onur Can Koyun, Behçet Ugur Töreyin

CoRR, 2024

HaLViT: Half of the Weights are Enough.

Onur Can Koyun, Behçet Ugur Töreyin

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Sievenet: An Efficient Model Utilizing H.265 Codec Structure for Video Object Detection.

Onur Can Koyun, Behçet Ugur Töreyin

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Focus-and-Detect: A small object detection framework for aerial images.

Onur Can Koyun, Reyhan Kevser Keser, Ibrahim Batuhan Akkaya, Behçet Ugur Töreyin

Signal Process. Image Commun., 2022

2019

Adversarial Nuclei Segmentation on H&E Stained Histopathology Images.

Onur Can Koyun, Tülay Yildirim

Proceedings of the IEEE International Symposium on INnovations in Intelligent SysTems and Applications, 2019