Abdullah Aydın Alatan

E-mail

alatan@metu.edu.tr

Department

Department of Electrical and Electronics Engineering

ORCID

0000-0001-5556-7301

Scopus Author ID

6701890979

Web of Science Researcher ID

E-3927-2012

Data Imbalance in Large-Scale Face Recognition B y k l ekli Y z Tanimada Veri Dengesizligi Erturkmen, Ahmet; Akkaya, Kursat; Boncu, Ece Selin; Ozden, Harun; Akbas, Emre; Alatan, Abdullah Aydın (2025-01-01) In this study, proposals have been presented to improve various recognition problems encountered in large-scale face databases related to the open-set face recognition problem. Based on the experiments conducted, the most ...
TinyRS-R1: Compact Vision Language Model for Remote Sensing Köksal, Aybora; Alatan, Abdullah Aydın (2025-01-01) Remote sensing applications often rely on edge hardware that cannot host the models in the 7B parametric vision language of today. This paper presents TinyRS, the first 2B-parameter VLM optimized for remote sensing, and Ti...
BI-DIRECTIONAL TRACKLET EMBEDDING FOR MULTI-OBJECT TRACKING Bilgi, Halil Çağrı; Alatan, Abdullah Aydın (2024-10-17) The last decade has seen significant advancements in multi-object tracking, particularly with the emergence of deep learning based methods. However, many prior studies in online tracking have primarily focused on enhancing...
Causal Transformer for Fusion and Pose Estimation in Deep Visual Inertial Odometry Akman, Ahmet; Alatan, Abdullah Aydın; KURT, YUNUS BİLGE (2024-09-30)
IG-SLAM: Instant Gaussian SLAM Sarıkamış, Furkan Aykut; Alatan, Abdullah Aydın (2024-09-30)
XoFTR: Cross-modal Feature Matching Transformer Tuzcuoğlu, Önder; Köksal, Aybora; Sofu, Buğra; Kalkan, Sinan; Alatan, Abdullah Aydın (2024-06-16) We introduce XoFTR a cross-modal cross-view method for local feature matching between thermal infrared (TIR) and visible images. Unlike visible images TIR images are less susceptible to adverse lighting and weather conditi...
Deep Metric Learning with Chance Constraints GÜRBÜZ, YETİ ZİYA; Alatan, Abdullah Aydın; CAN, OĞUL (2024-01-08)
Knowledge Distillation Layer that Lets the Student Decide GÖRGÜN, ADA; GÜRBÜZ, YETİ ZİYA; Alatan, Abdullah Aydın (2023-11-20)
GENERALIZABLE EMBEDDINGS WITH CROSS-BATCH METRIC LEARNING GÜRBÜZ, YETİ ZİYA; Alatan, Abdullah Aydın (2023-10-08) Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a c...
Generalized Sum Pooling for Metric Learning GÜRBÜZ, YETİ ZİYA; ŞENER, OZAN; Alatan, Abdullah Aydın (2023-10-02) A common architectural choice for deep metric learning is a convolutional neural network followed by global average pooling ( GAP). Albeit simple, GAP is a highly effective way to aggregate information. One possible explan...

Citation Formats