no code implementations • 8 Mar 2024 • Eda Yilmaz, Hacer Yalim Keles
Knowledge Distillation (KD) facilitates the transfer of discriminative capabilities from an advanced teacher model to a simpler student model, ensuring performance enhancement without compromising accuracy.
no code implementations • 13 Dec 2023 • Mojtaba Najafi Khatounabad, Hacer Yalim Keles, Selma Kadioglu
This study presents a deep learning-based approach to seismic velocity inversion problem, focusing on both noisy and noiseless training datasets of varying sizes.
no code implementations • 24 Oct 2021 • Ozge Mercanoglu Sincan, Hacer Yalim Keles
In this paper, we propose an isolated sign language recognition model based on a model trained using Motion History Images (MHI) that are generated from RGB video frames.
no code implementations • 2 Sep 2021 • Aakash Saboo, Sai Niranjan Ramachandran, Kai Dierkes, Hacer Yalim Keles
Disease-aware image editing by means of generative adversarial networks (GANs) constitutes a promising avenue for advancing the use of AI in the healthcare sector.
no code implementations • 11 May 2021 • Ozge Mercanoglu Sincan, Julio C. S. Jacques Junior, Sergio Escalera, Hacer Yalim Keles
However, several open challenges still need to be solved to allow SLR to be useful in practice.
no code implementations • 29 Mar 2021 • Ozlem Sen, Hacer Yalim Keles
The results of our experiments show that although individual classifiers for different sub-categories in the hierarchical scheme perform considerably well, the accumulation of the classification errors in the cascaded structure prevents its classification performance from exceeding that of the non-hierarchical deep model
1 code implementation • 18 Jan 2021 • Yahya Dogan, Hacer Yalim Keles
Most of these approaches use encoder-decoder architectures and have different limitations such as allowing unique results for a given image and a particular mask.
no code implementations • 3 Aug 2020 • Ozge Mercanoglu Sincan, Hacer Yalim Keles
In AUTSL random train-test splits, our models performed up to 95. 95% accuracy.
Ranked #7 on Sign Language Recognition on AUTSL
no code implementations • 19 Jun 2020 • Anil Osman Tur, Hacer Yalim Keles
Therefore, our analysis with deep features show that HMMs could also be utilized as well as deep sequence models in challenging isolated sign recognition problem.
no code implementations • 3 Jul 2019 • Yahya Dogan, Hacer Yalim Keles
The method to achieve this goal is to find an accurate latent vector representation of an image and a direction corresponding to the attribute.
1 code implementation • 4 Aug 2018 • Long Ang Lim, Hacer Yalim Keles
Foreground segmentation algorithms aim segmenting moving objects from the background in a robust way under various challenging scenarios.
1 code implementation • 7 Jan 2018 • Long Ang Lim, Hacer Yalim Keles
Our network takes an RGB image in three different scales and produces a foreground segmentation probability mask for the corresponding image.