Search Results for author: Sobhan Soleymani

Found 26 papers, 5 papers with code

Transporting Labels via Hierarchical Optimal Transport for Semi-Supervised Learning

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.

Image Classification

Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction

no code implementations29 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.

Multi-Task Learning

Attention Aware Wavelet-based Detection of Morphed Face Images

no code implementations29 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.

Face Recognition

Differential Morph Face Detection using Discriminative Wavelet Sub-bands

no code implementations24 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.

Face Detection Face Recognition

Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification

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.

Classification Self-Supervised Learning +1

Detection of Morphed Face Images Using Discriminative Wavelet Sub-bands

no code implementations16 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).

Face Recognition

Mutual Information Maximization on Disentangled Representations for Differential Morph Detection

no code implementations2 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.

Differential Morphed Face Detection Using Deep Siamese Networks

no code implementations2 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.

Decision Making Face Detection

SuperMix: Supervising the Mixing Data Augmentation

1 code implementation CVPR 2021 Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Nasser M. Nasrabadi

In this paper, we propose a supervised mixing augmentation method, termed SuperMix, which exploits the knowledge of a teacher to mix images based on their salient regions.

Data Augmentation General Classification +2

Boosting Deep Face Recognition via Disentangling Appearance and Geometry

no code implementations13 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.

Face Recognition Transfer Learning

Adversarial Examples to Fool Iris Recognition Systems

no code implementations21 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.

Code Generation Iris Recognition

Learning to Authenticate with Deep Multibiometric Hashing and Neural Network Decoding

no code implementations11 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.).

Binarization

GASL: Guided Attention for Sparsity Learning in Deep Neural Networks

1 code implementation7 Jan 2019 Amirsina Torfi, Rouzbeh A. Shirvani, Sobhan Soleymani, Naser M. Nasrabadi

The main goal of network pruning is imposing sparsity on the neural network by increasing the number of parameters with zero value in order to reduce the architecture size and the computational speedup.

Model Compression Network Pruning

Fast Geometrically-Perturbed Adversarial Faces

1 code implementation24 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.

Face Recognition

ID Preserving Generative Adversarial Network for Partial Latent Fingerprint Reconstruction

no code implementations31 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.

Deep Sketch-Photo Face Recognition Assisted by Facial Attributes

no code implementations31 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.

Face Recognition Face Verification

Multi-Level Feature Abstraction from Convolutional Neural Networks for Multimodal Biometric Identification

no code implementations3 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.

General Classification Person Identification

Generalized Bilinear Deep Convolutional Neural Networks for Multimodal Biometric Identification

no code implementations3 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.

Person Identification

Attribute-Centered Loss for Soft-Biometrics Guided Face Sketch-Photo Recognition

no code implementations9 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.

Attention-Based Guided Structured Sparsity of Deep Neural Networks

1 code implementation13 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.

Network Pruning

Cannot find the paper you are looking for? You can Submit a new open access paper.