Search Results for author:
Found 17 papers, 9 papers with code
Can Facial Uniqueness be Inferred from Impostor Scores?
In Biometrics, facial uniqueness is commonly inferred from impostor similarity scores.
Predicting Face Recognition Performance Using Image Quality
This paper proposes a data driven model to predict the performance of a face recognition system based on image quality features.
A Brain-inspired Algorithm for Training Highly Sparse Neural Networks
Concretely, by exploiting the cosine similarity metric to measure the importance of the connections, our proposed method, Cosine similarity-based and Random Topology Exploration (CTRE), evolves the topology of sparse neural networks by adding the most important connections to the network without calculating dense gradient in the backward.
Morphing Attack Detection -- Database, Evaluation Platform and Benchmarking
Further, we present a new online evaluation platform to test algorithms on sequestered data.
A survey of face recognition techniques under occlusion
As a part of this review, we introduce face detection under occlusion, a preliminary step in face recognition.
Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders
This method, named QuickSelection, introduces the strength of the neuron in sparse neural networks as a criterion to measure the feature importance.
Worst-Case Morphs: a Theoretical and a Practical Approach
Face Recognition (FR) systems have been shown to be vulnerable to morphing attacks.
Memory-free Online Change-point Detection: A Novel Neural Network Approach
We show that ALACPD, on average, ranks first among state-of-the-art CPD algorithms in terms of quality of the time series segmentation, and it is on par with the best performer in terms of the accuracy of the estimated change-points.
Toward Face Biometric De-identification using Adversarial Examples
The remarkable success of face recognition (FR) has endangered the privacy of internet users particularly in social media.
Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks
Feature selection that selects an informative subset of variables from data not only enhances the model interpretability and performance but also alleviates the resource demands.
A Survey on the Robustness of Computer Vision Models against Common Corruptions
The performance of computer vision models are susceptible to unexpected changes in input images, known as common corruptions (e. g. noise, blur, illumination changes, etc.
Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers
Efficiency in DNNs can be achieved through sparse connectivity and reducing the model size.
What do neural networks learn in image classification? A frequency shortcut perspective
Our results demonstrate that NNs tend to find simple solutions for classification, and what they learn first during training depends on the most distinctive frequency characteristics, which can be either low- or high-frequencies.
Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space
We train autoencoders with implicit and explicit regularization techniques to enforce linearity relations among the representations of different blur levels in the latent space.
DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning
We propose a data augmentation strategy, named DFM-X, that leverages knowledge about frequency shortcuts, encoded in Dominant Frequencies Maps computed for image classification models.
NeutrEx: A 3D Quality Component Measure on Facial Expression Neutrality
Accurate face recognition systems are increasingly important in sensitive applications like border control or migration management.
E2F-Net: Eyes-to-Face Inpainting via StyleGAN Latent Space
We further improve the StyleGAN output to find the optimal code in the latent space using a new optimization for GAN inversion technique.
