Improving Multi-scale Face Recognition Using VGGFace2

@inproceedings{Massoli2019ImprovingMF,
  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},
  year={2019}
}
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… Expand

Figures and Tables from this paper

Multi-Resolution Face Recognition with Drones
TLDR
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. Expand
Cross-resolution face recognition adversarial attacks
TLDR
This study harnesses several of the strongest adversarial attacks against deep learning-based face recognition systems considering the cross-resolution domain, and finds that the deep representation attacks represents a much dangerous menace to a face recognition system than the ones based on the classification output independently from the used metric. Expand
etection of Face Recognition Adversarial Attacks
Deep Learning methods have become state-of-the-art for solving tasks such as Face Recognition (FR). Unfortunately, despite their success, it has been pointed out that these learning models areExpand
ParSecureML: An Efficient Parallel Secure Machine Learning Framework on GPUs
TLDR
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. Expand
An Efficient Parallel Secure Machine Learning Framework on GPUs
TLDR
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. Expand
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 kullanilarakExpand
Similarity Search and Applications: 13th International Conference, SISAP 2020, Copenhagen, Denmark, September 30 – October 2, 2020, Proceedings
TLDR
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. Expand
Detection of Face Recognition Adversarial Attacks
TLDR
The work on adversarial samples detection in forensics mainly focused on detecting attacks against FR systems in which the learning model is typically used only as a features extractor, showing that such approach is generalizable to different types of offensives. Expand

References

SHOWING 1-10 OF 13 REFERENCES
Low Resolution Face Recognition Using a Two-Branch Deep Convolutional Neural Network Architecture
TLDR
The proposed couple mappings method significantly improves the recognition performance especially for very low resolution probe face images (11.4% improvement in recognition accuracy) and can reconstruct a high resolution image from its corresponding lowresolution probe image which is comparable with state-of-the-art super-resolution methods in terms of visual quality. Expand
Synthesis-based Robust Low Resolution Face Recognition
TLDR
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. Expand
A Discriminative Feature Learning Approach for Deep Face Recognition
TLDR
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. Expand
VGGFace2: A Dataset for Recognising Faces across Pose and Age
TLDR
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. Expand
Very low resolution face recognition problem
  • W. W. Zou, P. Yuen
  • Computer Science, Medicine
  • 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS)
  • 2010
TLDR
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. Expand
Face Super-Resolution Guided by Facial Component Heatmaps
TLDR
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. Expand
Deep Residual Learning for Image Recognition
TLDR
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. Expand
Simultaneous Hallucination and Recognition of Low-Resolution Faces Based on Singular Value Decomposition
  • Muwei Jian, K. Lam
  • Computer Science, Mathematics
  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2015
TLDR
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. Expand
Squeeze-and-Excitation Networks
  • Jie Hu, Li Shen, Gang Sun
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
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. Expand
Super-Identity Convolutional Neural Network for Face Hallucination
TLDR
This paper defines a super-identity loss to measure the identity difference between a hallucinated face and its corresponding high-resolution face within the hypersphere identity metric space and presents a domain-integrated training approach by constructing a robust identity metric for faces from these two domains. Expand
...
1
2
...