1 code implementation • 2 Jul 2021 • Davood Zabihzadeh, Zahraa Alitbi, Seyed Jalaleddin Mousavirad
The proposed ensemble of losses enforces the deep model to extract features that are consistent with all losses.
1 code implementation • 11 Jun 2021 • Karrar Al-Kaabi, Reza Monsefi, Davood Zabihzadeh
To address this limitation, we propose a framework to enhance the generalization power of existing DML methods in a Zero-Shot Learning (ZSL) setting by general yet discriminative representation learning and employing a class adversarial neural network.
no code implementations • 7 Oct 2020 • Davood Zabihzadeh, Amar Tuama, Ali Karami-Mollaee
An important challenge in metric learning is scalability to both size and dimension of input data.
1 code implementation • Knowledge-Based Systems 2019 • Davood Zabihzadeh, Reza Monsefi, Hadi Sadoghi Yazdi
Also, the present work is extended for learning in the feature space induced by an RKHS kernel.
1 code implementation • 26 Apr 2019 • Sumia Abdulhussien Razooqi Al-Obaidi, Davood Zabihzadeh, Hamideh Hajiabadi
In this paper, we formulate the metric learning problem using the Rescaled Hinge loss function and then develop an efficient algorithm based on HQ (Half-Quadratic) to solve the problem.
no code implementations • 5 Apr 2018 • Baida Hamdan, Davood Zabihzadeh, Monsefi Reza
To the best of our knowledge, this is the first local online similarity/distance learning framework based on PA (Passive/Aggressive).