Search Results for author: Alptekin Temizel

Found 30 papers, 15 papers with code

Augmentation Policy Generation for Image Classification Using Large Language Models

no code implementations17 Oct 2024 Ant Duru, Alptekin Temizel

Automated data augmentation methods have significantly improved the performance and generalization capability of deep learning models in image classification.

Data Augmentation Image Classification

TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problem

no code implementations17 Sep 2024 M. Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc, Alptekin Temizel

Recently, the centerline has become a popular representation of lanes due to its advantages in solving the road topology problem.

3D Lane Detection

State-of-the-Art in Nudity Classification: A Comparative Analysis

1 code implementation26 Dec 2023 Fatih Cagatay Akyon, Alptekin Temizel

This paper presents a comparative analysis of existing nudity classification techniques for classifying images based on the presence of nudity, with a focus on their application in content moderation.

Classification Image Classification

Deep Architectures for Content Moderation and Movie Content Rating

1 code implementation8 Dec 2022 Fatih Cagatay Akyon, Alptekin Temizel

Rating a video based on its content is an important step for classifying video age categories.

Action Recognition Genre classification

Sequence Models for Drone vs Bird Classification

no code implementations21 Jul 2022 Fatih Cagatay Akyon, Erdem Akagunduz, Sinan Onur Altinuc, Alptekin Temizel

Moreover, we propose a new drone vs. bird sequence classification dataset to train and evaluate the proposed architectures.

Classification object-detection +2

Evaluation and Analysis of Different Aggregation and Hyperparameter Selection Methods for Federated Brain Tumor Segmentation

1 code implementation16 Feb 2022 Ece Isik-Polat, Gorkem Polat, Altan Kocyigit, Alptekin Temizel

Availability of large, diverse, and multi-national datasets is crucial for the development of effective and clinically applicable AI systems in the medical imaging domain.

Brain Tumor Segmentation Federated Learning +1

Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection

6 code implementations14 Feb 2022 Fatih Cagatay Akyon, Sinan Onur Altinuc, Alptekin Temizel

In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection.

Object object-detection +1

Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation

1 code implementation9 Feb 2022 Gorkem Polat, Ilkay Ergenc, Haluk Tarik Kani, Yesim Ozen Alahdab, Ozlen Atug, Alptekin Temizel

Experimental evaluations show that models trained with CDW-CE outperform the models trained with conventional categorical cross-entropy and other commonly used loss functions which are designed for the ordinal regression problems.

Image Classification regression

Improving Perceptual Quality of Adversarial Images Using Perceptual Distance Minimization and Normalized Variance Weighting

no code implementations AAAI Workshop AdvML 2022 Berat Tuna Karli, Deniz Sen, Alptekin Temizel

We show that these methods could also be used in conjunction to improve the perceptual quality of adversarial examples and demonstrate the quantitative improvements on CIFAR-10 and NIPS2017 Adversarial Learning Challenge datasets.

Perceptual Distance

Automated question generation and question answering from Turkish texts

1 code implementation11 Nov 2021 Fatih Cagatay Akyon, Devrim Cavusoglu, Cemil Cengiz, Sinan Onur Altinuc, Alptekin Temizel

In this work, we fine-tune a multilingual T5 (mT5) transformer in a multi-task setting for QA, QG and answer extraction tasks using Turkish QA datasets.

Question Answering Question Generation +1

Imperceptible Adversarial Examples by Spatial Chroma-Shift

1 code implementation5 Aug 2021 Ayberk Aydın, Deniz Sen, Berat Tuna Karli, Oguz Hanoglu, Alptekin Temizel

Deep Neural Networks have been shown to be vulnerable to various kinds of adversarial perturbations.

Generative Data Augmentation for Vehicle Detection in Aerial Images

no code implementations9 Dec 2020 Hilmi Kumdakcı, Cihan Öngün, Alptekin Temizel

The experiments show that the method increases the Average Precision by up to 25. 2% and 25. 7% when integrated with Pluralistic and DeepFill respectively.

Data Augmentation

LPMNet: Latent Part Modification and Generation for 3D Point Clouds

1 code implementation8 Aug 2020 Cihan Öngün, Alptekin Temizel

In this paper, we focus on latent modification and generation of 3D point cloud object models with respect to their semantic parts.

Performance Analysis of Noise Subspace-based Narrowband Direction-of-Arrival (DOA) Estimation Algorithms on CPU and GPU

1 code implementation28 Jul 2020 Hamza Eray, Alptekin Temizel

High-performance computing of array signal processing problems is a critical task as real-time system performance is required for many applications.

Distributed, Parallel, and Cluster Computing Signal Processing

Optimization of XNOR Convolution for Binary Convolutional Neural Networks on GPU

1 code implementation28 Jul 2020 Mete Can Kaya, Alperen İnci, Alptekin Temizel

Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts.

Bit-level Parallelization of 3DES Encryption on GPU

1 code implementation21 Jul 2020 Kaan Furkan Altınok, Afşin Peker, Alptekin Temizel

Triple DES (3DES) is a standard fundamental encryption algorithm, used in several electronic payment applications and web browsers.

Cryptography and Security Distributed, Parallel, and Cluster Computing

Speaker and Posture Classification using Instantaneous Intraspeech Breathing Features

no code implementations25 May 2020 Atıl İlerialkan, Alptekin Temizel, Hüseyin Hacıhabiboğlu

Instantaneous magnitude features are extracted using the Hilbert-Huang transform (HHT) and fed into a CNN-GRU network for classification of recordings from the open intraspeech breathing sound dataset, BreathBase, that we collected for this study.

Action Detection Activity Detection +3

Attack Type Agnostic Perceptual Enhancement of Adversarial Images

no code implementations7 Mar 2019 Bilgin Aksoy, Alptekin Temizel

Adversarial images are samples that are intentionally modified to deceive machine learning systems.

Adversarial Attack Image Generation +1

Paired 3D Model Generation with Conditional Generative Adversarial Networks

1 code implementation9 Aug 2018 Cihan Öngün, Alptekin Temizel

Generative Adversarial Networks (GANs) are shown to be successful at generating new and realistic samples including 3D object models.

Image Generation

Multi-modal Egocentric Activity Recognition using Audio-Visual Features

no code implementations2 Jul 2018 Mehmet Ali Arabaci, Fatih Özkan, Elif Surer, Peter Jančovič, Alptekin Temizel

In this work, we propose a new framework for egocentric activity recognition problem based on combining audio-visual features with multi-kernel learning (MKL) and multi-kernel boosting (MKBoost).

Egocentric Activity Recognition Optical Flow Estimation

The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples

no code implementations28 Mar 2018 Ayse Elvan Aydemir, Alptekin Temizel, Tugba Taskaya Temizel

To be immune to such attacks, it is desirable to have a pre-processing mechanism which removes these effects causing misclassification while keeping the content of the image.

Blocking Image Compression

Boosted Multiple Kernel Learning for First-Person Activity Recognition

no code implementations22 Feb 2017 Fatih Ozkan, Mehmet Ali Arabaci, Elif Surer, Alptekin Temizel

Activity recognition from first-person (ego-centric) videos has recently gained attention due to the increasing ubiquity of the wearable cameras.

Activity Recognition

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