A Deep Matrix Factorization Method for Learning Attribute Representations

Trigeorgis, George; Bousmalis, Konstantinos; Zafeiriou, Stefanos; Schuller, Björn

doi:10.1109/tpami.2016.2554555

Cited by 325 publications

(274 citation statements)

References 46 publications

Supporting

Mentioning

269

Contrasting

Order By: Relevance

“…Another important issue that can affect the performance of pre-classification is the structure of Deep Semi-NMF. As empirically verified in [36], the two-layer model is generally sufficient to achieve good performance, and a higher number of layers does not seem to lead to significant improvements. Therefore, we implement Deep Semi-NMF with a first hidden representation H 1 with 2h 2 /3 features, and a second representation H 2 with h 2 /2 features.…”

Section: Strategy For Pre-classificationmentioning

confidence: 72%

“…By further factorizing the mapping W, we can automatically learn the hidden representations and obtain better higher-level feature representations of the original data matrix V. Inspired by this, Trigeorgis et al [36] proposed Deep Semi-NMF, which applies Semi-NMF to a multi-layer structure in order to learn hidden representations of the original data matrix. Specifically, the input data matrix is factorized into m + 1 factors as follows:…”

Section: Deep Semi-nmfmentioning

confidence: 99%

“…By doing this, the model can find low-dimensional representations of the input data matrix. In [36], the Deep Semi-NMF model is able to outperform the single-layer Semi-NMF in a human face identification task. In [37], Deep NMF is utilized in speech separation, and the experimental results show that Deep NMF outperforms the single-layer NMF in terms of the source-to-distortion ratio (SDR).…”

Section: Deep Semi-nmfmentioning

confidence: 99%

See 2 more Smart Citations

Change Detection in SAR Images Based on Deep Semi-NMF and SVD Networks

et al. 2017

View full text Add to dashboard Cite

Abstract:With the development of Earth observation programs, more and more multi-temporal synthetic aperture radar (SAR) data are available from remote sensing platforms. Therefore, it is demanding to develop unsupervised methods for SAR image change detection. Recently, deep learning-based methods have displayed promising performance for remote sensing image analysis. However, these methods can only provide excellent performance when the number of training samples is sufficiently large. In this paper, a novel simple method for SAR image change detection is proposed. The proposed method uses two singular value decomposition (SVD) analyses to learn the non-linear relations between multi-temporal images. By this means, the proposed method can generate more representative feature expressions with fewer samples. Therefore, it provides a simple yet effective way to be designed and trained easily. Firstly, deep semi-nonnegative matrix factorization (Deep Semi-NMF) is utilized to select pixels that have a high probability of being changed or unchanged as samples. Next, image patches centered at these sample pixels are generated from the input multi-temporal SAR images. Then, we build SVD networks, which are comprised of two SVD convolutional layers and one histogram feature generation layer. Finally, pixels in both multi-temporal SAR images are classified by the SVD networks, and then the final change map can be obtained. The experimental results of three SAR datasets have demonstrated the effectiveness and robustness of the proposed method.

show abstract

Section: Strategy For Pre-classificationmentioning

confidence: 72%

Section: Deep Semi-nmfmentioning

confidence: 99%

Section: Deep Semi-nmfmentioning

confidence: 99%

See 1 more Smart Citation

Change Detection in SAR Images Based on Deep Semi-NMF and SVD Networks

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The deep learning reaches the two types of approaches. As for the latent factor approaches, the deep learning is applied for improving the performance of several algorithms such as factorization machine, matrix factorization, probabilistic matrix factorization, and K nearest neighbors' algorithm [25]- [28].…”

Section: Deep Collaborative Filtering Recommendationmentioning

confidence: 99%

Deep Learning-Based Recommendation: Current Issues and Challenges

Fakhfakh¹,

Ammar²,

Amar³

2017

ijacsa

View full text Add to dashboard Cite

Abstract-Due to the revolutionary advances of deep learning achieved in the field of computer vision, object recognition and natural language processing, the deep learning gained much attention. The recommendation task is influenced by the deep learning trend which shows its significant effectiveness. The deep learning based recommender models provides a better detention of user preferences, item features and users-items interactions history. In this paper, we provide a recent literature review of researches dealing with deep learning based recommendation approaches which is preceded by a presentation of the main lines of the recommendation approaches and the deep learning techniques. Then we finish by presenting the recommendation approach adopted by the most popular video recommendation platform YouTube which is based essentially on deep learning advances.

show abstract

“…Hence, a single optimal manifold cannot well describe the intrinsic structure of the original space. Although some studies exploited the intrinsic manifold structure by constructing the neighbour graph with different weighting schemes (i.e., 0-1, heat kernel and dot product) [23,24], the representation is relatively weak without considering the property of local neighbours. Consequently, the discriminative ability of the learned features is weak, which further influences the performance of target recognition.…”

Section: Introductionmentioning

confidence: 99%

SAR Target Recognition via Local Sparse Representation of Multi-Manifold Regularized Low-Rank Approximation

Dong

Fan

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:The extraction of a valuable set of features and the design of a discriminative classifier are crucial for target recognition in SAR image. Although various features and classifiers have been proposed over the years, target recognition under extended operating conditions (EOCs) is still a challenging problem, e.g., target with configuration variation, different capture orientations, and articulation. To address these problems, this paper presents a new strategy for target recognition. We first propose a low-dimensional representation model via incorporating multi-manifold regularization term into the low-rank matrix factorization framework. Two rules, pairwise similarity and local linearity, are employed for constructing multiple manifold regularization. By alternately optimizing the matrix factorization and manifold selection, the feature representation model can not only acquire the optimal low-rank approximation of original samples, but also capture the intrinsic manifold structure information. Then, to take full advantage of the local structure property of features and further improve the discriminative ability, local sparse representation is proposed for classification. Finally, extensive experiments on moving and stationary target acquisition and recognition (MSTAR) database demonstrate the effectiveness of the proposed strategy, including target recognition under EOCs, as well as the capability of small training size.

show abstract

A Deep Matrix Factorization Method for Learning Attribute Representations

Cited by 325 publications

References 46 publications

Change Detection in SAR Images Based on Deep Semi-NMF and SVD Networks

Change Detection in SAR Images Based on Deep Semi-NMF and SVD Networks

Deep Learning-Based Recommendation: Current Issues and Challenges

SAR Target Recognition via Local Sparse Representation of Multi-Manifold Regularized Low-Rank Approximation

Contact Info

Product

Resources

About