no code implementations • ECCV 2020 • Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
Semi-Supervised Learning (SSL) based on Convolutional Neural Networks (CNNs) have recently been proven as powerful tools for standard tasks such as image classification when there is not a sufficient amount of labeled data available during the training.
1 code implementation • 6 Dec 2024 • Sahar Rahimi Malakshan, Mohammad Saeed Ebrahimi Saadabadi, Ali Dabouei, Nasser M. Nasrabadi
Conventionally, DC relies on a costly bi-level optimization which prohibits its practicality.
no code implementations • 14 Aug 2024 • Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Seyed Rasoul Hosseini, Nasser M. Nasrabadi
While deep face recognition models have demonstrated remarkable performance, they often struggle on the inputs from domains beyond their training data.
no code implementations • 22 Jul 2024 • David Keaton, Amol S. Joshi, Jeremy Dawson, Nasser M. Nasrabadi
The challenge of deblurring fingerphoto images, or generating a sharp fingerphoto from a given blurry one, is a significant problem in the realm of computer vision.
2 code implementations • 20 Jul 2024 • Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Ali Dabouei, Nasser M. Nasrabadi
Aiming to enhance Face Recognition (FR) on Low-Quality (LQ) inputs, recent studies suggest incorporating synthetic LQ samples into training.
no code implementations • 12 Jul 2024 • Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta, Nasser M. Nasrabadi, Barbara J. Thompson, Michael S. F. Kirk, Daniel da Silva
In this work, we introduce an architecture based on the Transformer model, which is specifically designed to capture both local and global information from input images in an effective and efficient manner.
no code implementations • CVPR 2024 • Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta, Nasser M. Nasrabadi
The global spatial context is built upon the Transformer, which is specifically designed for image compression tasks.
no code implementations • 22 Jan 2024 • Shoaib Meraj Sami, Md Mahedi Hasan, Nasser M. Nasrabadi, Raghuveer Rao
The transductive transfer learning (TTL) method that incorporates a CycleGAN-based unpaired domain translation network has been previously proposed in the literature for effective ATR annotation.
no code implementations • 5 Jan 2024 • Niloufar Alipour Talemi, Hossein Kashiani, Nasser M. Nasrabadi
In this paper, we propose a novel multi-branch neural network that leverages SB attribute information to boost the performance of FR.
no code implementations • 6 Nov 2023 • Ali Zafari, Atefeh Khoshkhahtinat, Jeremy A. Grajeda, Piyush M. Mehta, Nasser M. Nasrabadi, Laura E. Boucheron, Barbara J. Thompson, Michael S. F. Kirk, Daniel da Silva
In this work, we propose an adversarially trained neural network, equipped with local and non-local attention modules to capture both the local and global structure of the image resulting in a better trade-off in rate-distortion (RD) compared to conventional hand-engineered codecs.
no code implementations • 22 Sep 2023 • Mohammad Akyash, Ali Zafari, Nasser M. Nasrabadi
The consistent improvement we observed in these benchmarks demonstrates the efficacy of our approach in enhancing FR performance.
no code implementations • 19 Sep 2023 • Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta, Mohammad Akyash, Hossein Kashiani, Nasser M. Nasrabadi
In addition, we introduce a novel entropy model that incorporates two different hyperpriors to model cross-channel and spatial dependencies of the latent representation.
no code implementations • 19 Sep 2023 • Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta, Nasser M. Nasrabadi, Barbara J. Thompson, Michael S. F. Kirk, Daniel da Silva
NASA's Solar Dynamics Observatory (SDO) mission collects large data volumes of the Sun's daily activity.
no code implementations • 19 Sep 2023 • Ali Zafari, Atefeh Khoshkhahtinat, Piyush M. Mehta, Nasser M. Nasrabadi, Barbara J. Thompson, Michael S. F. Kirk, Daniel da Silva
Recently successful end-to-end optimized neural network-based image compression systems have shown great potential to be used in an ad-hoc manner.
no code implementations • 20 Aug 2023 • Hossein Kashiani, Niloufar Alipour Talemi, Mohammad Saeed Ebrahimi Saadabadi, Nasser M. Nasrabadi
The proposed consistency regularization aligns the abstraction in the hidden layers of our model across the morph attack images which are generated from diverse domains in the wild.
no code implementations • 18 Aug 2023 • Sahar Rahimi Malakshan, Mohammad Saeed Ebrahimi Saadabadi, Nima Najafzadeh, Nasser M. Nasrabadi
Deep convolutional neural networks have achieved remarkable success in face recognition (FR), partly due to the abundant data availability.
no code implementations • 18 Aug 2023 • Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Hossein Kashiani, Nasser M. Nasrabadi
However, these methods have shown a significant decline in performance when applied to real-world low-resolution benchmarks like TinyFace or SCFace.
no code implementations • 14 Aug 2023 • Niloufar Alipour Talemi, Hossein Kashiani, Sahar Rahimi Malakshan, Mohammad Saeed Ebrahimi Saadabadi, Nima Najafzadeh, Mohammad Akyash, Nasser M. Nasrabadi
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.
no code implementations • 4 Aug 2023 • Ali Zafari, Atefeh Khoshkhahtinat, Piyush Mehta, Mohammad Saeed Ebrahimi Saadabadi, Mohammad Akyash, Nasser M. Nasrabadi
The design of a neural image compression network is governed by how well the entropy model matches the true distribution of the latent code.
no code implementations • 6 Jun 2023 • Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Ali Zafari, Moktari Mostofa, Nasser M. Nasrabadi
Our method adaptively finds and assigns more attention to the recognizable low-quality samples in the training datasets.
no code implementations • 23 May 2023 • Shoaib M. Sami, Nasser M. Nasrabadi, Raghuveer Rao
We employ a CycleGAN model to transfer the mid-wave infrared (MWIR) images to visible (VIS) domain images (or visible to MWIR domain).
no code implementations • 18 Oct 2022 • 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.
no code implementations • 12 Oct 2022 • Ali Zafari, Atefeh Khoshkhahtinat, Piyush M. Mehta, Nasser M. Nasrabadi, Barbara J. Thompson, Daniel da Silva, Michael S. F. Kirk
We have designed an ad-hoc ANN-based image compression scheme to reduce the amount of data needed to be stored and retrieved on space missions studying solar dynamics.
no code implementations • 16 Sep 2022 • Hossein Kashiani, Shoaib Meraj Sami, Sobhan Soleymani, Nasser M. Nasrabadi
In this paper, we intend to learn a morph detection model with high generalization to a wide range of morphing attacks and high robustness against different adversarial attacks.
no code implementations • 15 Sep 2022 • Moktari Mostofa, Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Nasser M. Nasrabadi
Second, we develop a novel pose attention block (PAB) to specially guide the pose-agnostic feature extraction from profile faces.
no code implementations • 7 Sep 2022 • Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Sobhan Soleymani, Moktari Mostofa, Nasser M. Nasrabadi
In this paper, we seek to draw connections between the frontal and profile face images in an abstract embedding space.
no code implementations • 2 Sep 2022 • Ali Dabouei, Fariborz Taherkhani, Sobhan Soleymani, Nasser M. Nasrabadi
This phenomenon hinders the outer optimization in AT since the convergence rate of MSGD is highly dependent on the variance of the gradients.
no code implementations • 28 Jun 2022 • Paria Jeihouni, Omid Dehzangi, Annahita Amireskandari, Ali Rezai, Nasser M. Nasrabadi
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 layers.
no code implementations • 10 Jun 2022 • Paria Jeihouni, Omid Dehzangi, Annahita Amireskandari, Ali Dabouei, Ali Rezai, Nasser M. Nasrabadi
Our ablation study results on the WVU-OCT data-set in five-fold cross-validation (5-CV) suggest that the proposed MultiSDGAN with a serial attention module provides the most competitive performance, and guiding the spatial attention feature maps by binary masks further improves the performance in our proposed network.
no code implementations • 10 Dec 2021 • Sobhan Soleymani, Ali Dabouei, Fariborz Taherkhani, Seyed Mehdi Iranmanesh, Jeremy Dawson, Nasser M. Nasrabadi
The first loss assures that the representations of modalities for a class have comparable magnitudes to provide a better quality estimation, while the multimodal representations of different classes are distributed to achieve maximum discrimination in the embedding space.
no code implementations • 29 Nov 2021 • Poorya Aghdaie, Baaria Chaudhary, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
As such, instead of using images in the RGB domain, we decompose every image into its wavelet sub-bands using 2D wavelet decomposition and a deep supervised feature selection scheme is employed to find the most discriminative wavelet sub-bands of input images.
no code implementations • 4 Nov 2021 • Salman Mohamadi, Gianfranco. Doretto, Nasser M. Nasrabadi, Donald A. Adjeroh
In this line, we propose a new framework for human age estimation using information from human dermal fibroblast gene expression data.
no code implementations • 3 Nov 2021 • Kelsey O'Haire, Sobhan Soleymani, Baaria Chaudhary, Poorya Aghdaie, Jeremy Dawson, Nasser M. Nasrabadi
In this paper, we explore combination of two methods for morphed image generation, those of geometric transformation (warping and blending to create morphed images) and photometric perturbation.
no code implementations • 2 Nov 2021 • Veeru Talreja, Nasser M. Nasrabadi, Matthew C. Valenti
In recent years, periocular recognition has been developed as a valuable biometric identification approach, especially in wild environments (for example, masked faces due to COVID-19 pandemic) where facial recognition may not be applicable.
no code implementations • 24 Oct 2021 • Uche Osahor, Nasser M. Nasrabadi
Generative adversarial models that capture salient low-level features which convey visual information in correlation with the human visual system (HVS) still suffer from perceptible image degradations.
no code implementations • 18 Oct 2021 • Uche Osahor, Nasser M. Nasrabadi
In few-shot classification, the primary goal is to learn representations from a few samples that generalize well for novel classes.
no code implementations • 12 Aug 2021 • Uche M. Osahor, Nasser M. Nasrabadi
Target detection systems identify targets by localizing their coordinates on the input image of interest.
no code implementations • 3 Aug 2021 • Moktari Mostofa, Salman Mohamadi, Jeremy Dawson, Nasser M. Nasrabadi
In the second approach, we design a coupled generative adversarial network (cpGAN) architecture consisting of a pair of cGAN modules that project the VIS and NIR iris images into a low-dimensional embedding domain to ensure maximum pairwise similarity between the feature vectors from the two iris modalities of the same subject.
no code implementations • 29 Jul 2021 • Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
In this paper, we propose a new method to leverage features from human attributes for person ReID.
no code implementations • 29 Jul 2021 • Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
To address this problem, we use a new Multi-Task Learning (MTL) paradigm in which a facial attribute predictor uses the knowledge of other related attributes to obtain a better generalization performance.
no code implementations • 29 Jul 2021 • Fariborz Taherkhani, Veeru Talreja, Jeremy Dawson, Matthew C. Valenti, Nasser M. Nasrabadi
We have evaluated the performance of cpCNN and ADDA and compared it with the proposed cpGAN.
no code implementations • 29 Jun 2021 • Poorya Aghdaie, Baaria Chaudhary, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
Morphed images have exploited loopholes in the face recognition checkpoints, e. g., Credential Authentication Technology (CAT), used by Transportation Security Administration (TSA), which is a non-trivial security concern.
no code implementations • 24 Jun 2021 • Baaria Chaudhary, Poorya Aghdaie, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
For some of the sub-bands, there is a marked difference between the entropy of the sub-band in a bona fide image and the identical sub-band's entropy in a morphed image.
no code implementations • 21 Jun 2021 • Amol S. Joshi, Ali Dabouei, Jeremy Dawson, Nasser M. Nasrabadi
It is added to generate ridge maps to ensure that fingerprint information and minutiae are preserved in the deblurring process and prevent the model from generating erroneous minutiae.
no code implementations • CVPR 2021 • Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
The goal is to use Wasserstein metric to provide pseudo labels for the unlabeled images to train a Convolutional Neural Networks (CNN) in a Semi-Supervised Learning (SSL) manner for the classification task.
no code implementations • 16 Jun 2021 • Poorya Aghdaie, Baaria Chaudhary, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
To detect morphing attacks, we propose a method which is based on a discriminative 2D Discrete Wavelet Transform (2D-DWT).
no code implementations • 7 Feb 2021 • Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi
However, GANs overlook the explicit data density characteristics which leads to undesirable quantitative evaluations and mode collapse.
no code implementations • 7 Jan 2021 • Domenick Poster, Matthew Thielke, Robert Nguyen, Srinivasan Rajaraman, Xing Di, Cedric Nimpa Fondje, Vishal M. Patel, Nathaniel J. Short, Benjamin S. Riggan, Nasser M. Nasrabadi, Shuowen Hu
Thermal face imagery, which captures the naturally emitted heat from the face, is limited in availability compared to face imagery in the visible spectrum.
no code implementations • 4 Dec 2020 • Fariborz Taherkhani, Hadi Kazemi, Ali Dabouei, Jeremy Dawson, Nasser M. Nasrabadi
Semi-Supervised Learning (SSL) approaches have been an influential framework for the usage of unlabeled data when there is not a sufficient amount of labeled data available over the course of training.
no code implementations • 2 Dec 2020 • Sobhan Soleymani, Ali Dabouei, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi
The network is trained by triplets of face images, in which the intermediate image inherits the landmarks from one image and the appearance from the other image.
no code implementations • 2 Dec 2020 • Sobhan Soleymani, Baaria Chaudhary, Ali Dabouei, Jeremy Dawson, Nasser M. Nasrabadi
Although biometric facial recognition systems are fast becoming part of security applications, these systems are still vulnerable to morphing attacks, in which a facial reference image can be verified as two or more separate identities.
no code implementations • 9 Oct 2020 • Moktari Mostofa, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi
Cross-spectral iris recognition is emerging as a promising biometric approach to authenticating the identity of individuals.
no code implementations • 4 Sep 2020 • Seyed Mehdi Iranmanesh, Ali Dabouei, Nasser M. Nasrabadi
We present a novel framework to exploit privileged information for recognition which is provided only during the training phase.
no code implementations • 28 Jul 2020 • Saba Heidari Gheshlaghi, Omid Dehzangi, Ali Dabouei, Annahita Amireskandari, Ali Rezai, Nasser M. Nasrabadi
We incorporate the Unet architecture in the NAS framework as its backbone for the segmentation of the retinal layers in our collected and pre-processed OCT image dataset.
no code implementations • 3 May 2020 • Moktari Mostofa, Syeda Nyma Ferdous, Benjamin S. Riggan, Nasser M. Nasrabadi
However, aerial vehicle detection on super-resolved images remains a challenging task due to the lack of discriminative information in the super-resolved images.
no code implementations • 25 Apr 2020 • Fariborz Taherkhani, Veeru Talreja, Jeremy Dawson, Matthew C. Valenti, Nasser M. Nasrabadi
In this paper, we hypothesize that the profile face domain possesses a gradual connection with the frontal face domain in the deep feature space.
no code implementations • 3 Apr 2020 • Fariborz Taherkhani, Veeru Talreja, Matthew C. Valenti, Nasser M. Nasrabadi
The DNDCMH network consists of two separatecomponents: an attribute-based deep cross-modal hashing (ADCMH) module, which uses a margin (m)-based loss function toefficiently learn compact binary codes to preserve similarity between modalities in the Hamming space, and a neural error correctingdecoder (NECD), which is an error correcting decoder implemented with a neural network.
2 code implementations • CVPR 2021 • Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Nasser M. Nasrabadi
On the distillation task, solely classifying images mixed using the teacher's knowledge achieves comparable performance to the state-of-the-art distillation methods.
no code implementations • 13 Jan 2020 • Ali Dabouei, Fariborz Taherkhani, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
We demonstrate that the proposed approach enhances the performance of deep face recognition models by assisting the training process in two ways.
no code implementations • 7 Jan 2020 • Seyed Mehdi Iranmanesh, Ali Dabouei, Sobhan Soleymani, Hadi Kazemi, Nasser M. Nasrabadi
In this work, we present a practical approach to the problem of facial landmark detection.
1 code implementation • 8 Oct 2019 • Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi
Deep neural networks are susceptible to adversarial manipulations in the input domain.
no code implementations • 17 Sep 2019 • Hadi Kazemi, Fariborz Taherkhani, Nasser M. Nasrabadi
First, we propose a multi-scale generator architecture for face hallucination with a high up-scaling ratio factor, which has multiple intermediate outputs at different resolutions.
no code implementations • 15 Aug 2019 • Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi
In this book chapter, we propose a new Convolutional Neural Network (CNN) framework which adopts a structural sparsity learning technique to select the optimal spectral bands to obtain the best face recognition performance over all of the spectral bands.
no code implementations • 8 Aug 2019 • Sobhan Soleymani, Ali Dabouei, Jeremy Dawson, Nasser M. Nasrabadi
Deep neural networks have presented impressive performance in biometric applications.
no code implementations • 5 Aug 2019 • Veeru Talreja, Matthew C. Valenti, Nasser M. Nasrabadi
The proposed architecture consists of two major components: a deep hashing (DH) component, which is used for robust mapping of face images to their corresponding intermediate binary codes, and a NND component, which corrects errors in the intermediate binary codes that are caused by differences in the enrollment and probe biometrics due to factors such as variation in pose, illumination, and other factors.
no code implementations • 5 Aug 2019 • Veeru Talreja, Fariborz Taherkhani, Matthew C. Valenti, Nasser M. Nasrabadi
In this paper, we propose a novel attribute-guided cross-resolution (low-resolution to high-resolution) face recognition framework that leverages a coupled generative adversarial network (GAN) structure with adversarial training to find the hidden relationship between the low-resolution and high-resolution images in a latent common embedding subspace.
no code implementations • 27 Jul 2019 • Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi
In this paper, we present an attribute-guided deep coupled learning framework to address the problem of matching polarimetric thermal face photos against a gallery of visible faces.
no code implementations • 21 Jun 2019 • Sobhan Soleymani, Ali Dabouei, Jeremy Dawson, Nasser M. Nasrabadi
Therefore, to compensate for this shortcoming, we propose to train a deep auto-encoder surrogate network to mimic the conventional iris code generation procedure.
no code implementations • 11 Feb 2019 • Veeru Talreja, Sobhan Soleymani, Matthew C. Valenti, Nasser M. Nasrabadi
The MDHND consists of two separate modules: a multimodal deep hashing (MDH) module, which is used for feature-level fusion and binarization of multiple biometrics, and a neural network decoder (NND) module, which is used to refine the intermediate binary codes generated by the MDH and compensate for the difference between enrollment and probe biometrics (variations in pose, illumination, etc.).
no code implementations • 11 Feb 2019 • Veeru Talreja, Fariborz Taherkhani, Matthew C. Valenti, Nasser M. Nasrabadi
With benefits of fast query speed and low storage cost, hashing-based image retrieval approaches have garnered considerable attention from the research community.
no code implementations • NeurIPS 2018 • Hadi Kazemi, Sobhan Soleymani, Fariborz Taherkhani, Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi
These approaches usually fail to model domain-specific information which has no representation in the target domain.
no code implementations • 14 Nov 2018 • Hadi Kazemi, Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi
This paper describes the Style and Content Disentangled GAN (SC-GAN), a new unsupervised algorithm for training GANs that learns disentangled style and content representations of the data.
no code implementations • 12 Oct 2018 • Hadi Kazemi, Fariborz Taherkhani, Nasser M. Nasrabadi
In contrast to current unsupervised image-to-image translation techniques, our framework leverages a novel perceptual discriminator to learn the geometry of human face.
1 code implementation • 24 Sep 2018 • Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
The state-of-the-art performance of deep learning algorithms has led to a considerable increase in the utilization of machine learning in security-sensitive and critical applications.
no code implementations • 26 Aug 2018 • Amir Soleimani, Nasser M. Nasrabadi, Elias Griffith, Jason Ralph, Simon Maskell
This paper investigates the problem of aerial vehicle recognition using a text-guided deep convolutional neural network classifier.
no code implementations • 31 Jul 2018 • Sobhan Soleymani, Ali Dabouei, Seyed Mehdi Iranmanesh, Hadi Kazemi, Jeremy Dawson, Nasser M. Nasrabadi
In this paper a novel cross-device text-independent speaker verification architecture is proposed.
no code implementations • 31 Jul 2018 • Ali Dabouei, Sobhan Soleymani, Hadi Kazemi, Seyed Mehdi Iranmanesh, Jeremy Dawson, Nasser M. Nasrabadi
We achieved the rank-10 accuracy of 88. 02\% on the IIIT-Delhi latent fingerprint database for the task of latent-to-latent matching and rank-50 accuracy of 70. 89\% on the IIIT-Delhi MOLF database for the task of latent-to-sensor matching.
no code implementations • 31 Jul 2018 • Seyed Mehdi Iranmanesh, Hadi Kazemi, Sobhan Soleymani, Ali Dabouei, Nasser M. Nasrabadi
The proposed Attribute-Assisted Deep Con- volutional Neural Network (AADCNN) method exploits the facial attributes and leverages the loss functions from the facial attributes identification and face verification tasks in order to learn rich discriminative features in a common em- bedding subspace.
no code implementations • 16 Jul 2018 • Amir Soleimani, Nasser M. Nasrabadi
The low resolution of objects of interest in aerial images makes pedestrian detection and action detection extremely challenging tasks.
no code implementations • 3 Jul 2018 • Sobhan Soleymani, Amirsina Torfi, Jeremy Dawson, Nasser M. Nasrabadi
We demonstrate that, rather than spatial fusion at the convolutional layers, the fusion can be performed on the outputs of the fully-connected layers of the modality-specific CNNs without any loss of performance and with significant reduction in the number of parameters.
no code implementations • 3 Jul 2018 • Sobhan Soleymani, Ali Dabouei, Hadi Kazemi, Jeremy Dawson, Nasser M. Nasrabadi
Multiple features are extracted at several different convolutional layers from each modality-specific CNN for joint feature fusion, optimization, and classification.
no code implementations • 20 Apr 2018 • Fariborz Taherkhani, Nasser M. Nasrabadi, Jeremy Dawson
In this paper, we propose a new deep framework which predicts facial attributes and leverage it as a soft modality to improve face identification performance.
no code implementations • 9 Apr 2018 • Hadi Kazemi, Sobhan Soleymani, Ali Dabouei, Mehdi Iranmanesh, Nasser M. Nasrabadi
Specifically, an attribute-centered loss is proposed which learns several distinct centers, in a shared embedding space, for photos and sketches with different combinations of attributes.
1 code implementation • 13 Feb 2018 • Amirsina Torfi, Rouzbeh A. Shirvani, Sobhan Soleymani, Nasser M. Nasrabadi
Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed.
no code implementations • 4 Jan 2018 • Seyed Mehdi Iranmanesh, Ali Dabouei, Hadi Kazemi, Nasser M. Nasrabadi
we propose a coupled deep neural network architecture which leverages relatively large visible and thermal datasets to overcome the problem of overfitting and eventually we train it by a polarimetric thermal face dataset which is the first of its kind.
no code implementations • 3 Jan 2018 • Ali Dabouei, Hadi Kazemi, Seyed Mehdi Iranmanesh, Jeremi Dawson, Nasser M. Nasrabadi
Elastic distortion of fingerprints has a negative effect on the performance of fingerprint recognition systems.
1 code implementation • 20 Dec 2017 • Oytun Ulutan, Benjamin S. Riggan, Nasser M. Nasrabadi, B. S. Manjunath
We propose a new order preserving bilinear framework that exploits low-resolution video for person detection in a multi-modal setting using deep neural networks.
no code implementations • 7 Aug 2017 • Veeru Talreja, Matthew C. Valenti, Nasser M. Nasrabadi
In this paper, we propose a secure multibiometric system that uses deep neural networks and error-correction coding.
2 code implementations • 18 Jun 2017 • Amirsina Torfi, Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi, Jeremy Dawson
We propose the use of a coupled 3D Convolutional Neural Network (3D-CNN) architecture that can map both modalities into a representation space to evaluate the correspondence of audio-visual streams using the learned multimodal features.
5 code implementations • 26 May 2017 • Amirsina Torfi, Jeremy Dawson, Nasser M. Nasrabadi
In our paper, we propose an adaptive feature learning by utilizing the 3D-CNNs for direct speaker model creation in which, for both development and enrollment phases, an identical number of spoken utterances per speaker is fed to the network for representing the speakers' utterances and creation of the speaker model.
1 code implementation • 29 Jan 2017 • Xiaoxia Sun, Nasser M. Nasrabadi, Trac. D. Tran
In this paper, we describe the deep sparse coding network (SCN), a novel deep network that encodes intermediate representations with nonnegative sparse coding.
no code implementations • 21 Dec 2015 • Xiaoxia Sun, Nasser M. Nasrabadi, Trac. D. Tran
Sparse representation-based classifiers have shown outstanding accuracy and robustness in image classification tasks even with the presence of intense noise and occlusion.
no code implementations • 16 Jul 2015 • Tianpei Xie, Nasser M. Nasrabadi, Alfred O. Hero
In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set.
no code implementations • 5 Jul 2015 • Tianpei Xie, Nasser M. Nasrabadi, Alfred O. Hero III
In this paper, we consider multi-sensor classification when there is a large number of unlabeled samples.
no code implementations • 10 Feb 2015 • Soheil Bahrampour, Nasser M. Nasrabadi, Asok Ray, Kenneth W. Jenkins
In this paper, we propose a supervised dictionary learning algorithm in the kernel domain for hyperspectral image classification.
1 code implementation • 4 Feb 2015 • Soheil Bahrampour, Nasser M. Nasrabadi, Asok Ray, W. Kenneth Jenkins
Dictionary learning algorithms have been successfully used for both reconstructive and discriminative tasks, where an input signal is represented with a sparse linear combination of dictionary atoms.
no code implementations • 3 Feb 2015 • Xiaoxia Sun, Nasser M. Nasrabadi, Trac. D. Tran
We propose to enforce structured sparsity priors on the task-driven dictionary learning method in order to improve the performance of the hyperspectral classification.
no code implementations • 29 Oct 2014 • Minh Dao, Nam H. Nguyen, Nasser M. Nasrabadi, Trac. D. Tran
In this paper, we propose a general collaborative sparse representation framework for multi-sensor classification, which takes into account the correlations as well as complementary information between heterogeneous sensors simultaneously while considering joint sparsity within each sensor's observations.
no code implementations • CVPR 2014 • Soheil Bahrampour, Asok Ray, Nasser M. Nasrabadi, Kenneth W. Jenkins
An accelerated proximal algorithm is proposed to solve the optimization problem, which is an efficient tool for feature-level fusion among either homogeneous or heterogeneous sources of information.
no code implementations • 16 Jan 2014 • Xiaoxia Sun, Qing Qu, Nasser M. Nasrabadi, Trac. D. Tran
Pixel-wise classification, where each pixel is assigned to a predefined class, is one of the most important procedures in hyperspectral image (HSI) analysis.
no code implementations • NeurIPS 2011 • Nasser M. Nasrabadi, Trac. D. Tran, Nam Nguyen
Our second set of results applies to a general class of Gaussian design matrix $X$ with i. i. d rows $\oper N(0, \Sigma)$, for which we provide a surprising phenomenon: the extended Lasso can recover exact signed supports of both $\beta^{\star}$ and $e^{\star}$ from only $\Omega(k \log p \log n)$ observations, even the fraction of corruption is arbitrarily close to one.