Search Results for author: Savas Ozkan

Found 12 papers, 6 papers with code

Binarized Weight Error Networks With a Transition Regularization Term

no code implementations9 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.

Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss

1 code implementation12 Dec 2020 Savas Ozkan, Gozde Bozdagi Akar

This study proposes a novel framework for spectral unmixing by using 1D convolution kernels and spectral uncertainty.

Cross-Domain Segmentation with Adversarial Loss and Covariate Shift for Biomedical Imaging

no code implementations8 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.

Semantic Segmentation

Automatic Liver Segmentation with Adversarial Loss and Convolutional Neural Network

no code implementations28 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.

Liver Segmentation

Exploiting Local Indexing and Deep Feature Confidence Scores for Fast Image-to-Video Search

1 code implementation3 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.

Affine Transformation

Improved Deep Spectral Convolution Network For Hyperspectral Unmixing With Multinomial Mixture Kernel and Endmember Uncertainty

1 code implementation3 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.

Hyperspectral Unmixing

Deep Spectral Convolution Network for HyperSpectral Unmixing

1 code implementation22 Jun 2018 Savas Ozkan, Gozde Bozdagi Akar

In this paper, we propose a novel hyperspectral unmixing technique based on deep spectral convolution networks (DSCN).

Hyperspectral Unmixing

KinshipGAN: Synthesizing of Kinship Faces From Family Photos by Regularizing a Deep Face Network

no code implementations22 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.

Face Model

Cloud Detection From RGB Color Remote Sensing Images With Deep Pyramid Networks

no code implementations26 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.

Cloud Detection

Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction

2 code implementations24 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.

EndNet: Sparse AutoEncoder Network for Endmember Extraction and Hyperspectral Unmixing

1 code implementation6 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.

Hyperspectral Unmixing

Large-Scale Video Search with Efficient Temporal Voting Structure

no code implementations25 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.