Publications (13)
CNN-BiLSTM model for English Handwriting Recognition: Comprehensive Evaluation on the IAM Dataset
Firat Kizilirmak, Berrin Yanikoglu
We present a CNN-BiLSTM system for the problem of offline English handwriting recognition, with extensive evaluations on the public IAM dataset, including the effects of model size…
Relative Attribute Classification with Deep Rank SVM
Sara Atito Ali Ahmed, Berrin Yanikoglu
Relative attributes indicate the strength of a particular attribute between image pairs. We introduce a deep Siamese network with rank SVM loss function, called Deep Rank SVM (DRSV…
Dealing with Annotator Disagreement in Hate Speech Classification
Somaiyeh Dehghan, Mehmet Umut Sen, Berrin Yanikoglu
Hate speech detection is a crucial task, especially on social media where harmful content can spread quickly. Collecting social media content (tweets etc.) to train machine learnin…
COVID-19 Detection in Computed Tomography Images with 2D and 3D Approaches
Sara Atito Ali Ahmed, Mehmet Can Yavuz, Mehmet Umut Sen +9
Detecting COVID-19 in computed tomography (CT) or radiography images has been proposed as a supplement to the definitive RT-PCR test. We present a deep learning ensemble for detect…
Deep Convolutional Neural Network Ensembles using ECOC
Sara Atito Ali Ahmed, Cemre Zor, Berrin Yanikoglu +2
Deep neural networks have enhanced the performance of decision making systems in many applications including image understanding, and further gains can be achieved by constructing…
Variational Self-Supervised Learning
Mehmet Can Yavuz, Berrin Yanikoglu
We present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free repres…
Real or Virtual: A Video Conferencing Background Manipulation-Detection System
Ehsan Nowroozi, Yassine Mekdad, Mauro Conti +3
Recently, the popularity and wide use of the last-generation video conferencing technologies created an exponential growth in its market size. Such technology allows participants i…
GMM-Based Synthetic Samples for Classification of Hyperspectral Images With Limited Training Data
AmirAbbas Davari, Erchan Aptoula, Berrin Yanikoglu +2
The amount of training data that is required to train a classifier scales with the dimensionality of the feature data. In hyperspectral remote sensing, feature data can potentially…
Going Forward-Forward in Distributed Deep Learning
Ege Aktemur, Ege Zorlutuna, Kaan Bilgili +3
We introduce a new approach in distributed deep learning, utilizing Geoffrey Hinton's Forward-Forward (FF) algorithm to speed up the training of neural networks in distributed comp…
Hate Speech Detection in Turkish and Arabic: A Comprehensive Study
Somaiyeh Dehghan, Gökçe UludoÄan, Mehmet Umut Åen +3
Online hate speech has been linked to a global rise in violence against minorities, including incidents such as mass shootings, lynchings, and ethnic cleansing. Societies grappling…
Evaluating the Efficiency of Latent Spaces via the Coupling-Matrix
Mehmet Can Yavuz, Berrin Yanikoglu
A central challenge in representation learning is constructing latent embeddings that are both expressive and efficient. In practice, deep networks often produce redundant latent s…
Variance-Preserving Orthogonal Selection (VPOS): Greedy Feature Selection via Orthogonal Deflation in PCA Loading Space
Baran Koseoglu, Berrin Yanikoglu
We propose Variance-Preserving Orthogonal Selection (VPOS), a greedy framework for unsupervised feature selection that operates in the weighted PCA loading space. After each select…
Variational Self-Supervised Contrastive Learning Using Beta Divergence
Mehmet Can Yavuz, Berrin Yanikoglu
Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method whic…