Deep Face Recognition

By Omkar M. Parkhi, Andrea Vedaldi, Andrew Zisserman. 2015

5,654 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, methodology): “To date, numerous large scale face image datasets [22, 31, 13, 69, 37, 24, 41, 68, 15, 27, 46, 8, 39] have been proposed and fostered research and development for automated face detection [35, 21], alignment [66, 44], recognition [57, 49], generation [67, 5, 26, 58], modiﬁcation [3, 32, 19], and…”
Learning feed-forward one-shot learners (2016, background): “Training is usually performed by classifying pairs according to distance [5], or by enforcing a distance ranking with a triplet loss [16].”
Unsupervised Cross-Domain Image Generation (2016, methodology): “We then employed the VGG face CNN descriptor of Parkhi et al. (2015) in order to perform retrieval as follows.”
Certified Robustness to Adversarial Examples with Differential Privacy (2018, background): “rks (DNNs) perform exceptionally well on many machine learning tasks, including safety- and security-sensitive applications such as self-driving cars [5], malware classiﬁcation [48], face recognition [47], and critical infrastructure [71]. Robustness against malicious behavior is important in many o”
What is the State of Neural Network Pruning? (2020, background): “Another paper attributes their VGGNet to (Parkhi et al., 2015), which mentions three VGG networks.”
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks (2019, methodology): “Both models are derived from the VGG-Face model (16 layers), which is trained to recognize faces of 2, 622 people [27], [28].”
SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems (2018, methodology): “[34] with a VGG-16 architecture [49] trained on the VGG-Face dataset [41].”
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning (2017, methodology): “For VGG-Face, we leverage the pre-trained model released in [55], and only finetune the last softmax regression layer on our dataset.”
DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks (2019, background): “Deep Neural Networks (DNNs) have demonstrated their superior performance and are increasingly employed in various critical applications including face recognition, biomedical diagnosis, autonomous driving [Parkhi et al., 2015; Esteva et al., 2017; Redmon et al., 2016].”
Model-Reuse Attacks on Deep Learning Systems (2018, methodology): “In this case study, we use the VGG-VeryDeep-16model [46], which is pre-trained on the VGGFace dataset [46] consisting of the facial images of 2,622 identities.”
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks (2017, background): “Deep Neural Networks (DNNs) perform exceptionally well on many artificial intelligence tasks, including securitysensitive applications like malware classification [26] and face recognition [37].”
Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition (2016, methodology): “Similarly to Parkhi et al., we used 2d aﬃne alignment to align face images to a canonical pose at the input of the DNNs [33].”
Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer (2016, background): “For example, mid-level attention maps of a network trained for face recognition Parkhi et al. (2015) will have higher activations around eyes, nose and lips, and top level activation will correspond to full face (Fig.”
Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, methodology): “Neon: Neon3 is another open source DL framework based on Python with high performance for modern DNNs, such as AlexNet [37], Visual Geometry Group (VGG) [74], and GoogleNet [75].”
Defeating Image Obfuscation with Deep Learning (2016, methodology): “Zhou et al. [56] and Parkhi et al. [36] presented CNNs for the Labeled Faces in the Wild database [17] supplemented with large datasets of Web images.”
Adversarial Examples: Attacks and Defenses for Deep Learning (2017, methodology): “of eyeglass frames to attack a DNN-based FRS [101], which composes 11 blocks with 38 layers and 1 triplet loss function for feature embedding.”
Faceless Person Recognition: Privacy Implications in Social Media (2016, background): “Like other areas of computer vision, the last years have seen a shift from classifiers based on handcrafted features and metric learning approaches [13, 14, 15, 16, 17, 18, 19] towards methods based on deep learning [20, 21, 22, 23, 24, 25, 26, 27].”
Diversity in Faces (2019, methodology): “Several data sets such as IJBC [53], UMD [26] and VGGFace [22, 23] provide a larger set of face images with a wider range of pose and lighting variations.”