141 citations · 766 across the 81 of their papers we have counts for
104 papers
Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis
Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta +1
While replacing Gaussian decoders with a conditional diffusion model enhances the perceptual quality of reconstructions in neural image compression, their lack of inductive bias fo…
Neural-based Compression Scheme for Solar Image Data
Ali Zafari, Atefeh Khoshkhahtinat, Jeremy A. Grajeda +6
Studying the solar system and especially the Sun relies on the data gathered daily from space missions. These missions are data-intensive and compressing this data to make them eff…
Multi-spectral Entropy Constrained Neural Compression of Solar Imagery
Ali Zafari, Atefeh Khoshkhahtinat, Piyush M. Mehta +4
Missions studying the dynamic behaviour of the Sun are defined to capture multi-spectral images of the sun and transmit them to the ground station in a daily basis. To make transmi…
Trading-off Mutual Information on Feature Aggregation for Face Recognition
Mohammad Akyash, Ali Zafari, Nasser M. Nasrabadi
Despite the advances in the field of Face Recognition (FR), the precision of these methods is not yet sufficient. To improve the FR performance, this paper proposes a technique to…
Multi-Context Dual Hyper-Prior Neural Image Compression
Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta +3
Transform and entropy models are the two core components in deep image compression neural networks. Most existing learning-based image compression methods utilize convolutional-bas…
Context-Aware Neural Video Compression on Solar Dynamics Observatory
Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta +4
NASA's Solar Dynamics Observatory (SDO) mission collects large data volumes of the Sun's daily activity. Data compression is crucial for space missions to reduce data storage and v…
Towards Generalizable Morph Attack Detection with Consistency Regularization
Hossein Kashiani, Niloufar Alipour Talemi, Mohammad Saeed Ebrahimi Saadabadi +1
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 n…
Deep Boosting Multi-Modal Ensemble Face Recognition with Sample-Level Weighting
Sahar Rahimi Malakshan, Mohammad Saeed Ebrahimi Saadabadi, Nima Najafzadeh +1
Deep convolutional neural networks have achieved remarkable success in face recognition (FR), partly due to the abundant data availability. However, the current training benchmarks…
CCFace: Classification Consistency for Low-Resolution Face Recognition
Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Hossein Kashiani +1
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…
AAFACE: Attribute-aware Attentional Network for Face Recognition
Niloufar Alipour Talemi, Hossein Kashiani, Sahar Rahimi Malakshan +4
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 ma…
Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation
Md Mahedi Hasan, Nasser Nasrabadi
We introduce caption-guided face recognition (CGFR) as a new framework to improve the performance of commercial-off-the-shelf (COTS) face recognition (FR) systems. In contrast to c…
Frequency Disentangled Features in Neural Image Compression
Ali Zafari, Atefeh Khoshkhahtinat, Piyush Mehta +3
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 abi…
A Quality Aware Sample-to-Sample Comparison for Face Recognition
Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Ali Zafari +2
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…
Deep Transductive Transfer Learning for Automatic Target Recognition
Shoaib M. Sami, Nasser M. Nasrabadi, Raghuveer Rao
One of the major obstacles in designing an automatic target recognition (ATR) algorithm, is that there are often labeled images in one domain (i.e., infrared source domain) but no…
Landmark Enforcement and Style Manipulation for Generative Morphing
Samuel Price, Sobhan Soleymani, Nasser M. Nasrabadi
Morph images threaten Facial Recognition Systems (FRS) by presenting as multiple individuals, allowing an adversary to swap identities with another subject. Morph generation using…
Attention-Based Generative Neural Image Compression on Solar Dynamics Observatory
Ali Zafari, Atefeh Khoshkhahtinat, Piyush M. Mehta +4
NASA's Solar Dynamics Observatory (SDO) mission gathers 1.4 terabytes of data each day from its geosynchronous orbit in space. SDO data includes images of the Sun captured at diffe…
Robust Ensemble Morph Detection with Domain Generalization
Hossein Kashiani, Shoaib Meraj Sami, Sobhan Soleymani +1
Although a substantial amount of studies is dedicated to morph detection, most of them fail to generalize for morph faces outside of their training paradigm. Moreover, recent morph…
Pose Attention-Guided Profile-to-Frontal Face Recognition
Moktari Mostofa, Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan +1
In recent years, face recognition systems have achieved exceptional success due to promising advances in deep learning architectures. However, they still fail to achieve expected a…
Information Maximization for Extreme Pose Face Recognition
Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Sobhan Soleymani +2
In this paper, we seek to draw connections between the frontal and profile face images in an abstract embedding space. We exploit this connection using a coupled-encoder network to…
Revisiting Outer Optimization in Adversarial Training
Ali Dabouei, Fariborz Taherkhani, Sobhan Soleymani +1
Despite the fundamental distinction between adversarial and natural training (AT and NT), AT methods generally adopt momentum SGD (MSGD) for the outer optimization. This paper aims…
Benchmarking Human Face Similarity Using Identical Twins
Shoaib Meraj Sami, John McCauley, Sobhan Soleymani +2
The problem of distinguishing identical twins and non-twin look-alikes in automated facial recognition (FR) applications has become increasingly important with the widespread adopt…
GAN-based Super-Resolution and Segmentation of Retinal Layers in Optical coherence tomography Scans
Paria Jeihouni, Omid Dehzangi, Annahita Amireskandari +2
In this paper, we design a Generative Adversarial Network (GAN)-based solution for super-resolution and segmentation of optical coherence tomography (OCT) scans of the retinal laye…
Superresolution and Segmentation of OCT scans using Multi-Stage adversarial Guided Attention Training
Paria Jeihouni, Omid Dehzangi, Annahita Amireskandari +3
Optical coherence tomography (OCT) is one of the non-invasive and easy-to-acquire biomarkers (the thickness of the retinal layers, which is detectable within OCT scans) being inves…
Quality-Aware Multimodal Biometric Recognition
Sobhan Soleymani, Ali Dabouei, Fariborz Taherkhani +3
We present a quality-aware multimodal recognition framework that combines representations from multiple biometric traits with varying quality and number of samples to achieve incre…