no code implementations • 21 Dec 2023 • Ahmet Haydar Ornek, Deniz Sen, Esmanur Civil
The main aim of this study is to demonstrate how innovative view synthesis and 3D reconstruction techniques can be used to create models of endangered species using monocular RGB images.
no code implementations • 15 Dec 2023 • Selcuk Anil Karatopak, Deniz Sen
We hope this study to be influential for the usability of AI to preserve endangered animals; while the penultimate aim is to obtain a model that can output biologically consistent 3D models via small samples, the qualitative interpretation of an existing state-of-the-art model such as DreamGaussian will be a step forward in our goal.
no code implementations • 23 Jun 2023 • Enes Sadi Uysal, Deniz Sen, Ahmet Haydar Ornek, Ahmet Emin Yetkin
In this study, we propose a method for lesion detection on plant leaves utilizing class activation maps generated by a ResNet-18 classifier.
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.
no code implementations • AAAI Workshop AdvML 2022 • Deniz Sen, Berat Tuna Karli, Alptekin Temizel
Despite being very successful, deep learning models were shown to be vulnerable to crafted perturbations.
1 code implementation • 5 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.