Robust classwise and projective low-rank representation for image classification

Xue, Shengke; Jin, Xinyu

doi:10.1007/s11760-017-1136-1

Cited by 9 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For A ∈ R n1×n2×n3 , by using the Matlab notation, we defineĀ fft(A, [ ], 3), which is the discrete Fourier transformation of A along the third dimension. Likewise, we can compute A ifft(Ā, [ ], 3) through the inverse fft function.…”

Section: Notations and Preliminariesmentioning

confidence: 99%

“…More briefly,Ā =ŪSV T . Using the ifft function along the third dimension, we have 3). Definition 2.7 (tensor tubal rank and nuclear norm): For tensor A ∈ R n1×n2×n3 , its t-SVD is U * S * V T .…”

Section: Notations and Preliminariesmentioning

confidence: 99%

“…For tensor X ∈ R n1×n2×n3 , we haveX fft(X , [ ], 3). Note that the fft function runs along the third dimension.…”

Section: (A2)mentioning

confidence: 99%

“…Recovering missing values in high dimensional data has become increasingly attractive in computer vision. Exploring the intrinsic low-rank nature of incomplete data with limited observed elements has been widely applied in various applications, e.g., motion capture [1], image alignment [2], and image classification [3].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Low-Rank Tensor Completion by Truncated Nuclear Norm Regularization

Xue

Qiu

Liu

et al. 2018

2018 24th International Conference on Pattern Recognition (ICPR)

Self Cite

View full text Add to dashboard Cite

Currently, low-rank tensor completion has gained cumulative attention in recovering incomplete visual data whose partial elements are missing. By taking a color image or video as a three-dimensional (3D) tensor, previous studies have suggested several definitions of tensor nuclear norm. However, they have limitations and may not properly approximate the real rank of a tensor. Besides, they do not explicitly use the low-rank property in optimization. It is proved that the recently proposed truncated nuclear norm (TNN) can replace the traditional nuclear norm, as a better estimation to the rank of a matrix. Thus, this paper presents a new method called the tensor truncated nuclear norm (T-TNN), which proposes a new definition of tensor nuclear norm and extends the truncated nuclear norm from the matrix case to the tensor case. Beneficial from the low rankness of TNN, our approach improves the efficacy of tensor completion. We exploit the previously proposed tensor singular value decomposition and the alternating direction method of multipliers in optimization. Extensive experiments on real-world videos and images demonstrate that the performance of our approach is superior to those of existing methods.

show abstract

Section: Notations and Preliminariesmentioning

confidence: 99%

Section: Notations and Preliminariesmentioning

confidence: 99%

“…For tensor X ∈ R n1×n2×n3 , we haveX fft(X , [ ], 3). Note that the fft function runs along the third dimension.…”

Section: (A2)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Low-Rank Tensor Completion by Truncated Nuclear Norm Regularization

Xue

Qiu

Liu

et al. 2018

2018 24th International Conference on Pattern Recognition (ICPR)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Image classification [35] is a challenging task requiring a large amount of labeled dataset to train accurate models at optimal performance. With the advent of Deep Learning technologies, there is a huge demand in obtaining massive labeled dataset [21], [17].…”

Section: Introductionmentioning

confidence: 99%

Few-shot Classifier GAN

Ali-Gombe

Elyan

Savoye

et al. 2018

2018 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Fine-grained image classification with a few-shot classifier is a highly challenging open problem at the core of a numerous data labeling applications. In this paper, we present Few-shot Classifier Generative Adversarial Network as an approach for few-shot classification. We address the problem of few-shot classification by designing a GAN in which the discriminator and the generator compete to output labeled data in any case. In contrast to previous methods, our techniques generate then classify images into multiple fake or real classes. A key innovation of our adversarial approach is to allow fine-grained classification using multiple fake classes with semi-supervised deep learning. A major strength of our techniques lies in its label-agnostic characteristic, in the sense that the system handles both labeled and unlabeled data during training. We validate quantitatively our few-shot classifier on the MNIST and SVHN datasets by varying the ratio of labeled data over unlabeled data in the training set. Our quantitative analysis demonstrates that our techniques produce better classification performance when using multiple fake classes and larger amount of unlabelled data.

show abstract