Improving Multi-scale Face Recognition Using VGGFace2

  title={Improving Multi-scale Face Recognition Using VGGFace2},
  author={Fabio Valerio Massoli and Giuseppe Amato and F. Falchi and Claudio Gennaro and Claudio Vairo},
  booktitle={ICIAP Workshops},
Convolutional neural networks have reached extremely high performances on the Face Recognition task. These models are commonly trained by using high-resolution images and for this reason, their discrimination ability is usually degraded when they are tested against low-resolution images. Thus, Low-Resolution Face Recognition remains an open challenge for deep learning models. Such a scenario is of particular interest for surveillance systems in which it usually happens that a low-resolution… 

Multi-Resolution Face Recognition with Drones

This work studied the performance of deep neural networks for face re-identification specifically designed for low-quality images and applied them to a drone scenario using a publicly available dataset known as DroneSURF.

Cross-resolution face recognition adversarial attacks

Fine-tuning of Convolutional Neural Networks for the Recognition of Facial Expressions in Sign Language Video Samples

It is experimentally demonstrated that fine-tuning a pre-trained model along with data augmentation by horizontally flipping images and image normalization, helps in providing the best accuracy on the sign language dataset.

etection of Face Recognition Adversarial Attacks

This work presents its work on adversarial detection in forensics mainly focused on detecting attacks against FR systems in which the learning model is typically used only as features extractor, showing that such approach is generalizable to different classes of offensives.

ParSecureML: An Efficient Parallel Secure Machine Learning Framework on GPUs

This paper proposes a GPU-based framework ParSecureML to improve the performance of secure machine learning algorithms based on two-party computation, and is likely to be the first GPU- based secure machineLearning framework.

An Efficient Parallel Secure Machine Learning Framework on GPUs

This article proposes a GPU-based framework ParSecureML to improve the performance of secure machine learning algorithms based on two-party computation and integrates architecture specific optimizations, such as Tensor Cores, into Par secureML.

CNN-based Gender Prediction in Uncontrolled Environments

Uretilen ve toplanan veri miktarinin giderek artmasi ile birlikte yapay zekâ teknolojilerin kullanilmasi kacinilmaz hale gelmistir. Bu teknolojilerden biri olan derin ogrenme teknikleri kullanilarak

Similarity Search and Applications: 13th International Conference, SISAP 2020, Copenhagen, Denmark, September 30 – October 2, 2020, Proceedings

This paper presents a meta-analyses of keynotes interactive exploration using Hypergraphs to explore the role of language in the exploration of graph-based knowledge representation.



Synthesis-based Robust Low Resolution Face Recognition

An important feature of the algorithm is that it can handle resolution change along with illumination variations and also kernelize the algorithm to handle non-linearity in data and present a joint dictionary learning technique for robust recognition at low resolutions.

A Discriminative Feature Learning Approach for Deep Face Recognition

This paper proposes a new supervision signal, called center loss, for face recognition task, which simultaneously learns a center for deep features of each class and penalizes the distances between the deep features and their corresponding class centers.

VGGFace2: A Dataset for Recognising Faces across Pose and Age

A new large-scale face dataset named VGGFace2 is introduced, which contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject, and the automated and manual filtering stages to ensure a high accuracy for the images of each identity are described.

Very low resolution face recognition problem

  • W. W. ZouP. Yuen
  • Computer Science
    2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS)
  • 2010
Experimental results show that the proposed method outperforms the existing methods, in terms of image quality and recognition accuracy, as well as face super-resolution methods.

Face Super-Resolution Guided by Facial Component Heatmaps

This paper proposes a method that explicitly incorporates structural information of faces into the face super-resolution process by using a multi-task convolutional neural network (CNN) and achieves superior face hallucination results and outperforms the state-of-the-art.

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Simultaneous Hallucination and Recognition of Low-Resolution Faces Based on Singular Value Decomposition

  • Muwei JianK. Lam
  • Computer Science
    IEEE Transactions on Circuits and Systems for Video Technology
  • 2015
In this paper, singular values are first proved to be effective for representing face images, and the singular values of a face image at different resolutions have approximately a linear relation.

Squeeze-and-Excitation Networks

  • Jie HuLi ShenGang Sun
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
This work proposes a novel architectural unit, which is term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and finds that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost.

IARPA Janus Benchmark-B Face Dataset

The IARPA Janus Benchmark-B (NIST IJB-B) dataset is introduced, a superset of IJB -A that represents operational use cases including access point identification, forensic quality media searches, surveillance video searches, and clustering.