Deep Learning for Face Veriﬁcation

By Thapanapong Rukkanchanunt, T. Paine. 2013

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): “…[31] Celebrity 13K Model generated predictions no IMDB-WIKI [46] IMDB, WIKI 500K no FotW [13] Flickr 25K yes CACD [10] celebrity 160K no DiF [39] Flickr 1M **Skin color prediction † CelebA [37] CelebFace [54, 55] LFW [23] 200K no LFW+ [16] LFW [23 cability of computer vision methods to these ﬁelds.”
Convolutional Neural Network Architectures for Matching Natural Language Sentences (2014, background): “Matching structured objects rarely goes beyond estimating the similarity of objects in the same domain [23, 24, 19], with few exceptions like [2, 18].”
Deep Learning Face Representation by Joint Identification-Verification (2014, background): “In recent years, a great deal of efforts have been made for face recognition with deep learning [5, 10, 20, 27, 8, 22, 21].”
Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not? (2015, background): “Extensive works have been done to push the accuracy limit on it [3, 16, 4, 1, 2, 5, 11, 10, 12, 14, 13, 17, 9].”
Surpassing Human-Level Face Verification Performance on LFW with GaussianFace (2014, methodology): “Although there has been signiﬁcant work [22, 9, 5, 14, 47, 13, 59, 50, 51, 53] on LFW and the accuracy rate has been improved from 60.02% [56] to 97.35% [53] since LFW is established in 2007, these studies have not closed the gap to human-level performance [28] in face veriﬁcation.”
Deeply learned face representations are sparse, selective, and robust (2014, background): “Face recognition achieved great progress thanks to extensive research effort devoted to this area [36, 30, 18, 14, 1, 6, 15, 26, 7, 5, 27, 31, 29, 32, 28].”
Frankenstein: Learning Deep Face Representations Using Small Data (2016, unknown): “Since big data is important for learning a deep face representation, several research groups have collected large datasets with 90,000 up to 2.6 million labeled face images [5], [28], [31], [50], [62].”
RAPID: Rating Pictorial Aesthetics using Deep Learning (2014, background): “Despite the success of handcrafted and generic visual features, the usefulness of automatically learned features have been demonstrated in many vision applications [15, 4, 32, 30].”
Syntax-based Deep Matching of Short Texts (2015, background): “Deep Matching Models There are other works on using deep neural networks for the matching task [ Huang et al. , 2013; Bordes et al. , 2014; Sun et al. , 2013; Lu and Li, 2013; Hu et al. , 2014 ] , which build upon given or learned representations of objects.”
A Comprehensive Study on Center Loss for Deep Face Recognition (2019, background): “Deep face recognition Face recognition via deep learning has witnessed a series of breakthrough in recent years (Sun et al. 2013; Taigman et al. 2014; Sun et al. 2014a; Schroff et al. 2015; Parkhi et al. 2015; Wang et al. 2018a,b).”
DeepID3: Face Recognition with Very Deep Neural Networks (2015, methodology): “Motivated by both [12] and [14], an approach of learning deep face representation by joint face identiﬁcation-veriﬁcation was proposed in DeepID2 [13] and was further improved in DeepID2+ [15].”
Effective face frontalization in unconstrained images (2014, background): “…that pool information over large image regions, thereby accounting for possible misalignments due to pose changes (e.g., [20, 25, 33, 36]), by improving 2D face alignment accuracy [14, 15, 35], or by using massive face collections to learn pose-robust representations [13, 26, 27, 41].”
Look at Boundary: A Boundary-Aware Face Alignment Algorithm (2018, background): “Face alignment, which refers to facial landmark detection in this work, serves as a key step for many face applications, e.g., face recognition [75], face veriﬁcation [48, 49] and face frontalisation [21].”
Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI (2018, background): “Recently,deeplearninghasattractedincreasingattentioninthe ﬁ eld of machine learning and arti ﬁ cial intelligence and has been demonstrated to prodigiously improve learning performance in computer vision and image recognition (Lecun et al., 2015; Sun et al., 2013).”
Learning Social Relation Traits from Face Images (2015, methodology): “Summary for the labelled attributes in the datasets: AFLW [20], CelebFaces [33] and Kaggle Expression [10]. summarises the data.”