DeepFace: Closing the Gap to Human-Level Performance in Face Verification
By Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf. 2014
6,566 citations recorded by the source corpus.
In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers. Thus we trained it on the largest facial dataset to-date, an identity labeled dataset of four million facial images belonging to more than 4, 000 identities. The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier. Our method reaches an accuracy of 97.35% on the Labeled Faces in the Wild (LFW) dataset, reducing the error of the current state of the art by more than 27%, closely approaching human-level performance.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
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
- Luc Van Gool
- Dacheng Tao
- Xiaogang Wang
- Ming-Hsuan Yang
- Trevor Darrell
- Andrew Zisserman
- Bernt Schiele
- Jitendra Malik
In Signal Processing
- Xiaoming Liu
- Xiaoou Tang
- Weihong Deng
- Xiaogang Wang
- Ramalingam Chellappa
- Andrew Zisserman
- Dacheng Tao
- Mei Wang
Citations in the corpus
- Sequence to Sequence Learning with Neural Networks (2014, background): “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].”
- Supervised Learning of Universal Sentence Representations from Natural Language Inference Data (2017, background): “Striking examples include face recognition (Taigman et al., 2014) and visual question answering (Antol et al.”
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification (2015, background): “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].”
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (2014, background): “Deep-networks-based approaches have recently been substantially improving upon the state of the art in image classification [16, 31, 24], object detection [12, 33, 24], many other recognition tasks [22, 27, 32, 13], and even non-recognition tasks.”
- Local Relation Networks for Image Recognition (2019, neutral): “regular ω X all/one/no local ω X top-down group [17, 31] ω X group/one/no local ω X top-down depthwise [5, 11] ω X one/one/no local ω X top-down dilated [4, 33] ω X all/one/no atrous ω X top-down active [14] ω, Ω X all/one/no Ω ω X top-down local connected [25] ω ✗ all/one/no local ω X top-down dyna”
- FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, background): “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 at”
- Revisiting IM2GPS in the Deep Learning Era (2017, background): “Image retrieval using learned, deep representations is useful to a wide range of tasks such as product ranking [4, 12], sketch based image retrieval [25], face recognition [31, 26], cross-view localization [18, 37, 34] and scene retrieval [33, 2, 23, 8].”
- Webly Supervised Learning of Convolutional Networks (2015, methodology): “First we show that CNNs can be readily trained for easy categories with images retrieved by search engines with no bells or whistles.”
- Exploring Simple Siamese Representation Learning (2020, background): “Their applications include signature [4] and face [34] verification, tracking [3], one-shot learning [23], and others.”
- VAIN: Attentional Multi-agent Predictive Modeling (2017, neutral): “Deep Neural Networks (DNNs) have had much success in machine perception e.g. Computer Vision [1, 2, 3], Natural Language Processing [4] and Speech Recognition [5, 6].”
- FaceNet: A unified embedding for face recognition and clustering (2015, methodology): “[17], for example, performs a complex 3D alignment.”
- Speeding up Convolutional Neural Networks with Low Rank Expansions (2014, background): “The combination of an endto-end learning system with minimal need for human design decisions, and the ability to efficiently train large and complex models, have allowed them to achieve state-of-the-art performance in a number of benchmarks [10, 14, 19, 33, 37, 38].”
- Pay Less Attention with Lightweight and Dynamic Convolutions (2019, background): “Dynamic convolutions are similar to locally connected layers in the sense that the weights change at every position, however, the difference is that weights are dynamically generated by the model rather than fixed after training (LeCun et al., 1998; Taigman et al., 2014; Chen et al., 2015).”
- Deep Learning Face Attributes in the Wild (2014, background): “It becomes non-trivial if the filters are locally shared, while studies [27, 26] showed that locally shared filters perform better in face related tasks.”
- Learning both Weights and Connections for Efficient Neural Network (2015, background): “Deepface classified human faces with 120M parameters [5], and Coates et al.”
- Visual7W: Grounded Question Answering in Images (2015, background): “The recent development of deep learning technologies has achieved successes in many perceptual visual tasks such as object recognition, image classification and pose estimation [15, 21, 25, 38, 39, 42, 43].”
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images (2014, background): “Recently, these deep architectures have demonstrated impressive, state-of-the-art, and sometimes human-competitive results on many pattern recognition tasks, especially vision classification problems [16, 7, 31, 17].”