Search Results for author: Murat Tahtali

Found 4 papers, 0 papers with code

Learning Discriminative Representations for Multi-Label Image Recognition

no code implementations23 Jul 2021 Mohammed Hassanin, Ibrahim Radwan, Salman Khan, Murat Tahtali

Multi-label recognition is a fundamental, and yet is a challenging task in computer vision.

Mitigating the Impact of Adversarial Attacks in Very Deep Networks

no code implementations8 Dec 2020 Mohammed Hassanin, Ibrahim Radwan, Nour Moustafa, Murat Tahtali, Neeraj Kumar

In it, a Defensive Feature Layer (DFL) is integrated with a well-known DNN architecture which assists in neutralizing the effects of illegitimate perturbation samples in the feature space.

Data Poisoning

A Deep Marginal-Contrastive Defense against Adversarial Attacks on 1D Models

no code implementations8 Dec 2020 Mohammed Hassanin, Nour Moustafa, Murat Tahtali

Several research studies have been conducted to address this issue and build more robust deep learning models.

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