no code implementations • ICCV 2023 • Savas Ozkan, Mete Ozay, Tom Robinson
For this purpose, a novel latent space decomposition pipeline is introduced using transformer networks and generative models.
no code implementations • 9 May 2021 • Savas Ozkan, Gozde Bozdagi Akar
In addition, a novel regularization term is introduced that is suitable for all threshold-based binary precision networks.
1 code implementation • 12 Dec 2020 • Savas Ozkan, Gozde Bozdagi Akar
This study proposes a novel framework for spectral unmixing by using 1D convolution kernels and spectral uncertainty.
no code implementations • 8 Jun 2020 • Bora Baydar, Savas Ozkan, A. Emre Kavur, N. Sinem Gezer, M. Alper Selver, Gozde Bozdagi Akar
Despite the widespread use of deep learning methods for semantic segmentation of images that are acquired from a single source, clinicians often use multi-domain data for a detailed analysis.
no code implementations • 28 Nov 2018 • Bora Baydar, Savas Ozkan, Gozde Bozdagi Akar
Automatic segmentation of medical images is among most demanded works in the medical information field since it saves time of the experts in the field and avoids human error factors.
1 code implementation • 3 Aug 2018 • Savas Ozkan, Gozde Bozdagi Akar
The cost-effective visual representation and fast query-by-example search are two challenging goals that should be maintained for web-scale visual retrieval tasks on moderate hardware.
1 code implementation • 3 Aug 2018 • Savas Ozkan, Gozde Bozdagi Akar
The results validate that the proposed method obtains state-of-the-art hyperspectral unmixing performance particularly on the real datasets compared to the baseline techniques.
no code implementations • 22 Jun 2018 • Savas Ozkan, Akin Ozkan
In this paper, we propose a kinship generator network that can synthesize a possible child face by analyzing his/her parent's photo.
1 code implementation • 22 Jun 2018 • Savas Ozkan, Gozde Bozdagi Akar
In this paper, we propose a novel hyperspectral unmixing technique based on deep spectral convolution networks (DSCN).
no code implementations • 26 Jan 2018 • Savas Ozkan, Mehmet Efendioglu, Caner Demirpolat
Moreover, the method is able to obtain accurate pixel-level segmentation and classification results from a set of noisy labeled RGB color images.
3 code implementations • 24 Aug 2017 • Savas Ozkan, Gozde Bozdagi Akar
Frame-level visual features are generally aggregated in time with the techniques such as LSTM, Fisher Vectors, NetVLAD etc.
1 code implementation • 6 Aug 2017 • Savas Ozkan, Berk Kaya, Gozde Bozdagi Akar
Data acquired from multi-channel sensors is a highly valuable asset to interpret the environment for a variety of remote sensing applications.
no code implementations • 25 Jul 2016 • Ersin Esen, Savas Ozkan, Ilkay Atil
Our results show that the system can respond to video queries on a large video database with fast query times, high recall rate and very low memory and disk requirements.