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.
In this paper, we propose a new method to leverage features from human attributes for person ReID.
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.
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.
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.
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.
To detect morphing attacks, we propose a method which is based on a discriminative 2D Discrete Wavelet Transform (2D-DWT).
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.
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.
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.
We demonstrate that the proposed approach enhances the performance of deep face recognition models by assisting the training process in two ways.
In this work, we present a practical approach to the problem of facial landmark detection.
Deep neural networks are susceptible to adversarial manipulations in the input domain.
Therefore, to compensate for this shortcoming, we propose to train a deep auto-encoder surrogate network to mimic the conventional iris code generation procedure.
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.).
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.
These approaches usually fail to model domain-specific information which has no representation in the target domain.
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.
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.
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.
In this paper a novel cross-device text-independent speaker verification architecture is proposed.
Multiple features are extracted at several different convolutional layers from each modality-specific CNN for joint feature fusion, optimization, and classification.
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.
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.
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.