Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Akkaya, Ibrahim"'
Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) when trained from scratch on smaller datasets, possibly due to a lack of local inductive bias in the arch
Externí odkaz:
http://arxiv.org/abs/2305.08551
Autor:
Akkaya, Ibrahim Batuhan, Halici, Ugur
Unsupervised source-free domain adaptation methods aim to train a model for the target domain utilizing a pretrained source-domain model and unlabeled target-domain data, particularly when accessibility to source data is restricted due to intellectua
Externí odkaz:
http://arxiv.org/abs/2212.04227
Publikováno v:
Signal Processing: Image Communication, Volume 104, May 2022, 116675
Despite recent advances, object detection in aerial images is still a challenging task. Specific problems in aerial images makes the detection problem harder, such as small objects, densely packed objects, objects in different sizes and with differen
Externí odkaz:
http://arxiv.org/abs/2203.12976
Publikováno v:
In Pattern Recognition September 2024 153
Deep models trained on large-scale RGB image datasets have shown tremendous success. It is important to apply such deep models to real-world problems. However, these models suffer from a performance bottleneck under illumination changes. Thermal IR c
Externí odkaz:
http://arxiv.org/abs/2106.07165
Autor:
Akkaya, Ibrahim Batuhan, Halici, Ugur
Image-to-image translation (IIT) has made much progress recently with the development of adversarial learning. In most of the recent work, an adversarial loss is utilized to match the distributions of the translated and target image sets. However, th
Externí odkaz:
http://arxiv.org/abs/2009.00878
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Akkaya, Ibrahim, Tozburun, Serhat
Publikováno v:
Laser Resonators, Microresonators, and Beam Control XXIV.
Conference on Laser Resonators, Microresonators, and Beam Control XXIV at SPIE LASE Conference -- JAN 22-FEB 28, 2022 -- ELECTR NETWORK
In recent studies, high-speed optical coherence tomography (OCT) systems are gaining attention and are in hig
In recent studies, high-speed optical coherence tomography (OCT) systems are gaining attention and are in hig
Autor:
Tozburun, Serhat, Akkaya, Ibrahim
The laser source is the deciding factor in improving the rapid imaging of swept-source optical coherence tomography (OCT) systems. We introduce an intrinsically stable stretched-pulse mode -locking (SPML) laser operating a tuning range of over 92 nm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::666de9f1167ae8cecc1f09a8bb8d159e
https://hdl.handle.net/11454/76596
https://hdl.handle.net/11454/76596