Zobrazeno 1 - 10
of 163
pro vyhledávání: '"Saeed, Ebrahimi"'
Autor:
Malakshan, Sahar Rahimi, Saadabadi, Mohammad Saeed Ebrahimi, Dabouei, Ali, Nasrabadi, Nasser M.
Dataset Condensation (DC) aims to reduce deep neural networks training efforts by synthesizing a small dataset such that it will be as effective as the original large dataset. Conventionally, DC relies on a costly bi-level optimization which prohibit
Externí odkaz:
http://arxiv.org/abs/2412.04748
Autor:
Saadabadi, Mohammad Saeed Ebrahimi, Malakshan, Sahar Rahimi, Hosseini, Seyed Rasoul, Nasrabadi, Nasser M.
While deep face recognition models have demonstrated remarkable performance, they often struggle on the inputs from domains beyond their training data. Recent attempts aim to expand the training set by relying on computationally expensive and inheren
Externí odkaz:
http://arxiv.org/abs/2408.07642
Autor:
Saadabadi, Mohammad Saeed Ebrahimi, Malakshan, Sahar Rahimi, Dabouei, Ali, Nasrabadi, Nasser M.
Aiming to enhance Face Recognition (FR) on Low-Quality (LQ) inputs, recent studies suggest incorporating synthetic LQ samples into training. Although promising, the quality factors that are considered in these works are general rather than FR-specifi
Externí odkaz:
http://arxiv.org/abs/2407.14972
Autor:
Saadabadi, Mohammad Saeed Ebrahimi, Dabouei, Ali, Malakshan, Sahar Rahimi, Nasrabad, Nasser M.
Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a non-parametric classifier may provide better metric space utilization, it introd
Externí odkaz:
http://arxiv.org/abs/2403.16937
Autor:
Kashiani, Hossein, Talemi, Niloufar Alipour, Saadabadi, Mohammad Saeed Ebrahimi, Nasrabadi, Nasser M.
Though recent studies have made significant progress in morph attack detection by virtue of deep neural networks, they often fail to generalize well to unseen morph attacks. With numerous morph attacks emerging frequently, generalizable morph attack
Externí odkaz:
http://arxiv.org/abs/2308.10392
Autor:
Malakshan, Sahar Rahimi, Saadabadi, Mohammad Saeed Ebrahimi, Najafzadeh, Nima, Nasrabadi, Nasser M.
Deep convolutional neural networks have achieved remarkable success in face recognition (FR), partly due to the abundant data availability. However, the current training benchmarks exhibit an imbalanced quality distribution; most images are of high q
Externí odkaz:
http://arxiv.org/abs/2308.09234
Autor:
Saadabadi, Mohammad Saeed Ebrahimi, Malakshan, Sahar Rahimi, Kashiani, Hossein, Nasrabadi, Nasser M.
In recent years, deep face recognition methods have demonstrated impressive results on in-the-wild datasets. However, these methods have shown a significant decline in performance when applied to real-world low-resolution benchmarks like TinyFace or
Externí odkaz:
http://arxiv.org/abs/2308.09230
Autor:
Talemi, Niloufar Alipour, Kashiani, Hossein, Malakshan, Sahar Rahimi, Saadabadi, Mohammad Saeed Ebrahimi, Najafzadeh, Nima, Akyash, Mohammad, Nasrabadi, Nasser M.
In this paper, we present a new multi-branch neural network that simultaneously performs soft biometric (SB) prediction as an auxiliary modality and face recognition (FR) as the main task. Our proposed network named AAFace utilizes SB attributes to e
Externí odkaz:
http://arxiv.org/abs/2308.07243
Autor:
Zafari, Ali, Khoshkhahtinat, Atefeh, Mehta, Piyush, Saadabadi, Mohammad Saeed Ebrahimi, Akyash, Mohammad, Nasrabadi, Nasser M.
The design of a neural image compression network is governed by how well the entropy model matches the true distribution of the latent code. Apart from the model capacity, this ability is indirectly under the effect of how close the relaxed quantizat
Externí odkaz:
http://arxiv.org/abs/2308.02620
Autor:
Saadabadi, Mohammad Saeed Ebrahimi, Malakshan, Sahar Rahimi, Zafari, Ali, Mostofa, Moktari, Nasrabadi, Nasser M.
Currently available face datasets mainly consist of a large number of high-quality and a small number of low-quality samples. As a result, a Face Recognition (FR) network fails to learn the distribution of low-quality samples since they are less freq
Externí odkaz:
http://arxiv.org/abs/2306.04000