Erdem Akagündüz

E-mail

akaerdem@metu.edu.tr

Department

Graduate School of Informatics

ORCID

0000-0002-0792-7306

Scopus Author ID

8331988500

Web of Science Researcher ID

W-1788-2018

Exploring challenges in deep learning of single-station ground motion records Çağlar, Ümit Mert; Yilmaz, Baris; Türkmen, Melek; Akagündüz, Erdem; Tileylioglu, Salih (2025-12-01)
Augmenting atmospheric turbulence effects on thermal-adapted deep object detection models Uzun, Engin; Akagündüz, Erdem (2025-12-01) Atmospheric turbulence poses a significant challenge to the performance of object detection models. Turbulence causes distortions, blurring, and noise in images by bending and scattering light rays due to variations in the...
Infrared Domain Adaptation with Zero-Shot Quantization Sevsay, Burak; Akagündüz, Erdem (2025-01-01) Quantization is one of the most popular techniques for reducing computation time and shrinking model size. However, ensuring the accuracy of quantized models typically involves calibration using training data, which may be...
A Comparative Study of Multi-Task Learning Approaches on Disjoint Datasets Ayri sik Veri Setlerinde ok G revli grenme Yakla simlarinin Kar sila stirilmasi Yasin, Ahmed Hani; Akagündüz, Erdem; Demir, Ibrahim (2025-01-01) Multi-task learning is an approach that aims to use resources more efficiently during inference by concurrently learning multiple tasks through a single model. This method seeks to improve model generalization and performa...
Deep learning-based epicenter localization using single-station strong motion records Türkmen, Melek; Meral, Sanem; Yilmaz, Baris; Cikis, Melis; Akagündüz, Erdem; Tileylioglu, Salih (2025-01-01) This paper explores the application of deep learning (DL) techniques to strong motion records for single-station epicenter localization. Often underutilized in seismology-related studies, strong motion records contain rich...
Cross-Band Correlation-Aware Interactive Fusion for Multispectral Images Ulku, Irem; Tanriover, O. Ozgur; Akagündüz, Erdem (2025-01-01) Multispectral homogeneous bands capture distinct and complementary spectral characteristics, therefore, fusing multiple bands has the potential to increase semantic segmentation performance. However, the fusion of highly c...
Local Masking Meets Progressive Freezing: Crafting Efficient Vision Transformers for Self-Supervised Learning Topçuoğlu, Utku Mert; Akagündüz, Erdem (2025-01-01) This paper presents an innovative approach to self-supervised learning for Vision Transformers (ViTs), integrating local masked image modeling with progressive layer freezing. This method enhances the efficiency and speed ...
Local Masking Meets Progressive Freezing: Crafting Efficient Vision Transformers for Self-Supervised Learning Topçuoğlu, Utku Mert; Akagündüz, Erdem (2024-11-30)
Infrared domain adaptation with zero-shot quantization Sevsay, Burak; Akagündüz, Erdem (2024-11-30)
Deep Learning-based Average Shear Wave Velocity Prediction using Accelerometer Records Yilmaz, Baris; Turkmen, Melek; Meral, Sanem; Akagündüz, Erdem; Tileylioglu, Salih (2024-07-30)

Citation Formats