Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video

Huang, Zhiwu; Wang, Ruiping; Shan, Shiguang; Gool, Luc Van; Chen, Xilin

doi:10.1109/tpami.2017.2776154

Cited by 69 publications

(29 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Florian et al proposed the FaceNet with Triplet loss [48], which explicitly maximizes the inter-class distance and meanwhile minimizes the intra-class distance, where a margin term is used to determine the decision boundaries between positive and negative pairs. These methods and their improved versions have achieved good results in face recognition, and have also been applied to metric learning [26,47,67], fine-grained visual recognition [13,32,69] and person re-identification [22,33,36].…”

Section: Face Recognitionmentioning

confidence: 99%

Attacks on state-of-the-art face recognition using attentional adversarial attack generative network

Yang

Song

2020

Multimed Tools Appl

View full text Add to dashboard Cite

With the broad use of face recognition, its weakness gradually emerges that it is able to be attacked. Therefore, it is very important to study how face recognition networks are subject to attacks. Generating adversarial examples is an effective attack method, which misleads the face recognition system through obfuscation attack (rejecting a genuine subject) or impersonation attack (matching to an impostor). In this paper, we introduce a novel GAN, Attentional Adversarial Attack Generative Network (A 3 GN), to generate adversarial examples that mislead the network to identify someone as the target person not misclassify inconspicuously. For capturing the geometric and context information of the target person, this work adds a conditional variational autoencoder and attention modules to learn the instance-level correspondences between faces. Unlike traditional two-player GAN, this work introduces a face recognition network as the third player to participate in the competition between generator and discriminator which allows the attacker to impersonate the target person better. The generated faces which are hard to arouse the notice of onlookers can evade recognition by state-of-the-art networks and most of them are recognized as the target person.

show abstract

Section: Face Recognitionmentioning

confidence: 99%

Attacks on state-of-the-art face recognition using attentional adversarial attack generative network

Yang

Song

2020

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Referring to references [26,54,55], we needed to make strictly positive. Therefore, we let * , where E is the unit matrix and = trace 10 .…”

Section: Of 21mentioning

confidence: 99%

“…Lastly, unlike the RPNet proposed by reference [49], our RPCC does not involve the fusion of raw HSI data into an SVM, and there is no nonlinear activation operation. We used the same method as in references [29,54] to approximate the matrices in the Euclidean space. The source code will be released soon (https://github.com/whuyang/RPCC).…”

Section: Classification Based On Spectral-spatial Featuresmentioning

confidence: 99%

A Novel Hyperspectral Image Classification Pattern Using Random Patches Convolution and Local Covariance

2019

View full text Add to dashboard Cite

Today, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. However, such approaches are still hampered by long training times. Traditional spectral–spatial hyperspectral image classification only utilizes spectral features at the pixel level, without considering the correlation between local spectral signatures. Our article has tested a novel hyperspectral image classification pattern, using random-patches convolution and local covariance (RPCC). The RPCC is an effective two-branch method that, on the one hand, obtains a specified number of convolution kernels from the image space through a random strategy and, on the other hand, constructs a covariance matrix between different spectral bands by clustering local neighboring pixels. In our method, the spatial features come from multi-scale and multi-level convolutional layers. The spectral features represent the correlations between different bands. We use the support vector machine as well as spectral and spatial fusion matrices to obtain classification results. Through experiments, RPCC is tested with five excellent methods on three public data-sets. Quantitative and qualitative evaluation indicators indicate that the accuracy of our RPCC method can match or exceed the current state-of-the-art methods.

show abstract

“…However, DLSC algorithms rely on the linear operations of data points and traditional DLSC algorithms only deal with the data in Euclidean vector space. With the development of machine learning algorithms based on non-Euclidean data, the data on Riemannian manifolds such as Symmetric Positive Definite (SPD) manifold, Stiefel manifold and Grassmann manifold, has been widely used in computer vision tasks such as image set classification [5], face recognition [6], action recognition [7], object detection [8]. And Riemannian data has been proven to be more robust as the feature descriptors for images and videos than traditional Euclidean feature vectors.…”

Section: Introductionmentioning

confidence: 99%

“…And Riemannian data has been proven to be more robust as the feature descriptors for images and videos than traditional Euclidean feature vectors. Hence, Riemannian machine learning algorithms obtain extensive researches in the recent years and are successful in kernel learning [9], [10], [11], metric learning [12], [13], discriminant analysis [14], dimensionality reduction [15], and so on. We study the DSLC algorithm on SPD manifold in this paper.…”

Section: Introductionmentioning

confidence: 99%

Robust Dictionary Learning and Sparse Coding With Riemannian Geometry Preserving Method in Symmetric Matrices Inner Product Space

Zhang

Zhu

2020

IEEE Access

View full text Add to dashboard Cite

Existing Dictionary Learning and Sparse Coding (DLSC) algorithms for Symmetric Positive Definite (SPD) matrices usually adopt Reproducing Kernel Hilbert Space as workspace to perform necessary linear operations. But those methods heavily rely on ideal kernel maps and they are lack of robustness when facing different SPD data, especially in the case of high-sparsity coding. Different from existing methods, we explore a new workspace called Symmetric Matrices Inner Product Space (SMIPS) for modeling robust DLSC of SPD matrices. SMIPS, which can be treated as the minimal linear expansion space of SPD manifold, is a linear space equipped with a pre-defined inner product so it supports linear operations. Modelling DLSC in SMIPS is more intuitive, and SPD data can preserve matrix form in SMIPS. Then, in this paper, a Riemannian Geometry Preserving (RGP) method based on graph-regularized is proposed to include the Riemannian geometric information of original SPD data, so that improves the discriminability of sparse codes, and a sparse coding algorithm is developed to acquire sparse codes of SPD matrices in SMIPS efficiently, which extend the feature-sign search to such matrix space. For dictionary learning, an overall learning strategy utilizing the closed form solution of RGP codes is proposed to speed up the iterative dictionary learning process. Experiments on several computer vision tasks show that our algorithm is more robust even with high-sparsity coding across different datasets and outperforms other comparative algorithms in terms of recognition accuracy and learning efficiency, which also demonstrates the validity of SMIPS as a workspace.

show abstract

Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video

Cited by 69 publications

References 45 publications

Attacks on state-of-the-art face recognition using attentional adversarial attack generative network

Attacks on state-of-the-art face recognition using attentional adversarial attack generative network

A Novel Hyperspectral Image Classification Pattern Using Random Patches Convolution and Local Covariance

Robust Dictionary Learning and Sparse Coding With Riemannian Geometry Preserving Method in Symmetric Matrices Inner Product Space

Contact Info

Product

Resources

About