Fast High Dimensional Vector Multiplication Face Recognition

Barkan, Oren; Weill, Jonathan; Wolf, Lior; Aronowitz, Hagai

doi:10.1109/iccv.2013.246

Cited by 140 publications

(123 citation statements)

References 26 publications

Supporting

Mentioning

115

Contrasting

Order By: Relevance

“…[25], method using fast high dimensional vector multiplication by Barkan et al . [26] or robust feature set matching for partial face recognition by Weng et al . [27].…”

Section: Context and Related Workmentioning

confidence: 99%

Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval

Bhattarai

Sharma

Jurie

et al. 2015

Computer Vision - ECCV 2014 Workshops

View full text Add to dashboard Cite

Abstract. This paper presents a novel method for hierarchically organizing large face databases, with application to efficient identity-based face retrieval. The method relies on metric learning with local binary pattern (LBP) features. On one hand, LBP features have proved to be highly resilient to various appearance changes due to illumination and contrast variations while being extremely efficient to calculate. On the other hand, metric learning (ML) approaches have been proved very successful for face verification 'in the wild', i.e. in uncontrolled face images with large amounts of variations in pose, expression, appearances, lighting, etc. While such ML based approaches compress high dimensional features into low dimensional spaces using discriminatively learned projections, the complexity of retrieval is still significant for large scale databases (with millions of faces). The present paper shows that learning such discriminative projections locally while organizing the database hierarchically leads to a more accurate and efficient system. The proposed method is validated on the standard Labeled Faces in the Wild (LFW) benchmark dataset with millions of additional distracting face images collected from photos on the internet.

show abstract

“…[25], method using fast high dimensional vector multiplication by Barkan et al . [26] or robust feature set matching for partial face recognition by Weng et al . [27].…”

Section: Context and Related Workmentioning

confidence: 99%

Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval

Bhattarai

Sharma

Jurie

et al. 2015

Computer Vision - ECCV 2014 Workshops

View full text Add to dashboard Cite

show abstract

“…As can be seen from the table, the OBF surprisingly achieves 83.80% mean accuracy on LFW View 2 under unsupervised setting, which outperforms many specifically designed face representation methods such as LARK [38], POEM [5] and OCLBP [40]. The performance of OBF is even competitive to state-of-theart methods, which seems a proof of the saying that "Everything is in the face".…”

Section: Methodsmentioning

confidence: 52%

“…Mean Accuracy Rate(%) LHS [37] 73.40±0.40 LARK [38] 78.90 MRF-MLBP [39] 80.08±0.13 POEM [5] 82.71±0.59 OCLBP [40] 82.78±0.41 High-dim LBP [4] 84.08 High-dim LE [4] 84.58 I-LQP [6] 86.20±0.46 SFRD [14] 84.81 OBF 83.80±0.42 OBF (sqrt) 83.75±0.46…”

Section: Methodsmentioning

confidence: 99%

Everything is in the Face? Represent Faces with Object Bank

Liu

Shan

et al. 2015

Computer Vision - ACCV 2014 Workshops

View full text Add to dashboard Cite

Abstract. Object Bank (OB) [1] has been recently proposed as an object-level image representation for high-level visual recognition. OB represents an image from its responses to many pre-trained object filters. While OB has been validated in general image recognition tasks, it might seem ridiculous to represent a face with OB. However, in this paper, we study this anti-intuitive potential and show how OB can well represent faces amazingly, which seems a proof of the saying that "Everything is in the face". With OB representation, we achieve results better than many low-level features and even competitive to state-of-the-art methods on LFW dataset under unsupervised setting. We then show how we can achieve state of the art results by combining OB with some low-level feature (e.g. Gabor).

show abstract

“…Face recognition and verification systems based on aligned images acquired in controlled environments have made great strides in the last twenty years, being able to reduce the error rate by three orders of magnitude [18]. Most current approaches achieve state-of-the-art performance by exploring rich representations of the underlying visual content that consists of up to tens of thousands handcrafted features [1,4].…”

Section: Introductionmentioning

confidence: 99%

Rate-energy-accuracy optimization of convolutional architectures for face recognition

Bondi

Baroffio

Cesana

et al. 2016

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Face recognition systems based on Convolutional Neural Networks (CNNs) or Convolutional architectures currently represent the state of the art, achieving an accuracy comparable to that of humans. Nonetheless, there are two issues that might hinder their adoption on distributed battery-operated devices (e.g., visual sensor nodes, smartphones, and wearable devices). First, Convolutional architectures are usually computationally demanding, especially when the depth of the network is increased to maximize accuracy. Second, transmitting the output features produced by a CNN might require a bitrate higher than the one needed for coding the input image. Therefore, in this paper we address the problem of optimizing the energy-rate-accuracy characteristics of a convolutional architecture for face recognition. We carefully profile a CNN implementation on a Raspberry Pi device and optimize the structure of the neural network, achieving a 17-fold speedup without significantly affecting recognition accuracy. Moreover, we propose a coding architecture custom-tailored to features extracted by such model.

show abstract

Fast High Dimensional Vector Multiplication Face Recognition

Cited by 140 publications

References 26 publications

Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval

Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval

Everything is in the Face? Represent Faces with Object Bank

Rate-energy-accuracy optimization of convolutional architectures for face recognition

Contact Info

Product

Resources

About