DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Citations
[...]
38,208 citations
11,936 citations
Cites background from "DeepFace: Closing the Gap to Human-..."
...Deep Neural Networks (DNNs) are extremely powerful machine learning models that achieve excellent performance on difficult problems such as speech recogn iti n [13, 7] and visual object recognition [19, 6, 34, 21, 20]....
[...]
11,866 citations
Cites background from "DeepFace: Closing the Gap to Human-..."
...Convolutional neural networks (CNNs) [19, 18] have demonstrated recognition accuracy better than or comparable to humans in several visual recognition tasks, including recognizing traffic signs [3], faces [34, 32], and handwritten digits [3, 36]....
[...]
11,732 citations
8,289 citations
Cites background or methods from "DeepFace: Closing the Gap to Human-..."
...[17], for example, performs a complex 3D alignment....
[...]
...Previous face recognition approaches based on deep networks use a classification layer [15, 17] trained over a set of known face identities and then take an intermediate bottleneck layer as a representation used to generalize recognition beyond the set of identities used in training....
[...]
...The works of [15, 17, 23] all employ a complex system of multiple stages, that combines the output of a deep convolutional network with PCA for dimensionality reduction and an SVM for classification....
[...]
...[17] propose a multi-stage approach that aligns faces to a general 3D shape model....
[...]
...Similarly to other recent works which employ deep networks [15, 17], our approach is a purely data driven method which learns its representation directly from the pixels of the face....
[...]
References
73,978 citations
42,067 citations
23,814 citations
"DeepFace: Closing the Gap to Human-..." refers background or methods in this paper
...The gradients are computed by standard backpropagation of the error [25, 21]....
[...]
...[19] showed that very large and deep convolutional networks [21] trained by standard backpropagation [25] can achieve excellent recognition accuracy when trained on a large dataset....
[...]
7,767 citations
"DeepFace: Closing the Gap to Human-..." refers methods in this paper
...The proposed system differs from the majority of contributions in the field in that it uses the deep learning (DL) framework [3, 21] in lieu of well engineered features....
[...]
5,742 citations
"DeepFace: Closing the Gap to Human-..." refers background in this paper
...The LFW dataset [18] consists of 13,323 web photos of 5,749 celebrities which are divided into 6,000 face pairs in 10 splits....
[...]
...The mean recognition accuracy on LFW [18] marches steadily towards the human performance of over 97....
[...]