1 code implementation • 27 Jan 2023 • Omid Nejati Manzari, Hossein Kashiani, Hojat Asgarian Dehkordi, Shahriar Baradaran Shokouhi
In this paper, we explore the robustness of vision transformers against adversarial perturbations and try to enhance their robustness/accuracy trade-off in white box attack settings.
no code implementations • 13 Dec 2021 • Hojat Asgarian Dehkordi, Ali Soltani Nezhad, Hossein Kashiani, Shahriar Baradaran Shokouhi, Ahmad Ayatollahi
In this paper, we propose a two-phase multi-expert classification method for human action recognition to cope with long-tailed distribution by means of super-class learning and without any extra information.
no code implementations • 22 Aug 2020 • Hossein Kashiani, Amir Abbas Hamidi Imani, Shahriar Baradaran Shokouhi, Ahmad Ayatollahi
In this paper, we propose a domain adaptation approach to strengthen the contributions of the semantic background context.