Labeled Faces in the Wild: A Survey

By Eric Learned-Miller, Gary B. Huang, Aruni RoyChowdhury, Haoxiang Li, Gang Hua. 2016

485 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

Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning (2019, methodology): “…of each module, we leverage the evaluation protocol of the FaceNet [21] that trains the model using VGGFace2 dataset [2] and tests on LFW dataset [9] for face verification, and we utilize the evaluation protocol of the LMTCNN-2-1 [10] that trains and tests on Adience dataset [3] using five-fold…”
AgeDB: The First Manually Collected, In-the-Wild Age Database (2017, background): “More specifically, in 2007 the Labeled Faces “in-the-wild” (LFW) database [17, 23] was introduced.”
CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training (2017, methodology): “We use the FaceScrub dataset as training data, and test using the LFW [16] dataset.”
Deep Learning for Face Recognition: Pride or Prejudiced? (2019, background): “Deep Learning based systems show extremely high accuracy in many computer vision application such as object detection and recognition, and image synthesis [20, 22, 29].”
UMDFaces: An annotated face dataset for training deep networks (2016, background): “Recent progress in face detection, and recognition problems is also being driven by deep convolutional neural networks and large datasets [16].”
On Face Segmentation, Face Swapping, and Face Perception (2017, background): “We therefore see the use of a state of the art machine system as an adequate surrogate to human studies which often involve problems of their own [24].”
Learning One Class Representations for Face Presentation Attack Detection Using Multi-Channel Convolutional Neural Networks (2020, background): “Face recognition systems have matured a lot in recent years, and several approaches have reported human parity in the identification rate in ‘in the wild’ conditions [2].”
Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation (2018, methodology): “On the LFW dataset [60], we evaluate all student models in the task of face verification.”
Minimizing Latency for Secure Coded Computing Using Secret Sharing via Staircase Codes (2018, methodology): “The matrix A is a 42000× 250 matrix representing 56 images from the LFW dataset [48].”
Efficient Low-Resolution Face Recognition via Bridge Distillation (2020, methodology): “To validate the proposed approach, we conduct extensive experiments on three challenging public benchmarks: UMDFaces [51] dataset, LFW (Labeled Faces in the Wild) [52] dataset and UCCS (UnConstrained College Students) [53] dataset, for different evaluation tasks.”
Two-stage Image Classification Supervised by a Single Teacher Single Student Model (2019, methodology): “In this dataset, 3,425 videos from 1,595 different people were collected from the YouTube website and labeled according to the LFW image collection method [29].”
Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition (2017, background): “Labeled Faces in the Wild (LFW) VIS database [47] (rank-1 accuracy is greater than 99 percent).”