Search Results for author:
Found 33 papers, 5 papers with code
Transporting Labels via Hierarchical Optimal Transport for Semi-Supervised Learning
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.
Hyperspherical Classification with Dynamic Label-to-Prototype Assignment
Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative.
Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning
Orthogonal to the previous approaches to this limitation, we postulate that understanding the significance of the sentence components according to the target task can potentially enhance the performance of the models.
Synthetic Latent Fingerprint Generation Using Style Transfer
Limited data availability is a challenging problem in the latent fingerprint domain.
Revisiting Outer Optimization in Adversarial Training
This phenomenon hinders the outer optimization in AT since the convergence rate of MSGD is highly dependent on the variance of the gradients.
Superresolution and Segmentation of OCT scans using Multi-Stage adversarial Guided Attention Training
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.
Quality-Aware Multimodal Biometric Recognition
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.
Attribute Guided Sparse Tensor-Based Model for Person Re-Identification
In this paper, we propose a new method to leverage features from human attributes for person ReID.
Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction
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.
FDeblur-GAN: Fingerprint Deblurring using Generative Adversarial Network
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.
Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification
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.
Super-resolution Guided Pore Detection for Fingerprint Recognition
High recognition accuracy of the synthesized samples that is close to the accuracy achieved using the original high-resolution images validate the effectiveness of our proposed model.
Matching Distributions via Optimal Transport for Semi-Supervised Learning
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.
Differential Morphed Face Detection Using Deep Siamese Networks
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.
Mutual Information Maximization on Disentangled Representations for Differential Morph Detection
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.
Attribute Adaptive Margin Softmax Loss using Privileged Information
We present a novel framework to exploit privileged information for recognition which is provided only during the training phase.
Efficient OCT Image Segmentation Using Neural Architecture Search
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.
Exploiting Joint Robustness to Adversarial Perturbations
Recently, ensemble models have demonstrated empirical capabilities to alleviate the adversarial vulnerability.
Quality Guided Sketch-to-Photo Image Synthesis
We incorporate a hybrid discriminator which performs attribute classification of multiple target attributes, a quality guided encoder that minimizes the perceptual dissimilarity of the latent space embedding of the synthesized and real image at different layers in the network and an identity preserving network that maintains the identity of the synthesised image throughout the training process.
SuperMix: Supervising the Mixing Data Augmentation
On the distillation task, solely classifying images mixed using the teacher's knowledge achieves comparable performance to the state-of-the-art distillation methods.
Boosting Deep Face Recognition via Disentangling Appearance and Geometry
We demonstrate that the proposed approach enhances the performance of deep face recognition models by assisting the training process in two ways.
Robust Facial Landmark Detection via Aggregation on Geometrically Manipulated Faces
In this work, we present a practical approach to the problem of facial landmark detection.
SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations
Deep neural networks are susceptible to adversarial manipulations in the input domain.
Defending Against Adversarial Iris Examples Using Wavelet Decomposition
Deep neural networks have presented impressive performance in biometric applications.
Adversarial Examples to Fool Iris Recognition Systems
Therefore, to compensate for this shortcoming, we propose to train a deep auto-encoder surrogate network to mimic the conventional iris code generation procedure.
Fast Geometrically-Perturbed Adversarial Faces
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.
ID Preserving Generative Adversarial Network for Partial Latent Fingerprint Reconstruction
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
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.
Prosodic-Enhanced Siamese Convolutional Neural Networks for Cross-Device Text-Independent Speaker Verification
In this paper a novel cross-device text-independent speaker verification architecture is proposed.
Multi-Level Feature Abstraction from Convolutional Neural Networks for Multimodal Biometric Identification
Multiple features are extracted at several different convolutional layers from each modality-specific CNN for joint feature fusion, optimization, and classification.
Attribute-Centered Loss for Soft-Biometrics Guided Face Sketch-Photo Recognition
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.
Deep Cross Polarimetric Thermal-to-visible Face Recognition
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.
Fingerprint Distortion Rectification using Deep Convolutional Neural Networks
Elastic distortion of fingerprints has a negative effect on the performance of fingerprint recognition systems.
