Deep Closed-Form Subspace Clustering

Seo, Junghoon; Koo, Jamyoung; Jeon, Taegyun

doi:10.1109/iccvw.2019.00077

Cited by 12 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as discussed in Section 1, a significant disadvantage of iterative linear SC approaches, including k-SC, is that they require the dimension of each subspace to be known in advance. Instead of changing the architecture, Seo et al [93] proposed an efficient optimization framework for DSC-Net which uses a closed-form solution for deriving the weights of the self-expressive layer using Lagrangian multipliers. However, not only the obtained accuracy is lower than DSC-Net, but also the computational complexity is still quadratic in the number of samples.…”

Section: Scalable Nonlinear Sc Approachesmentioning

confidence: 99%

Beyond Linear Subspace Clustering: A Comparative Study of Nonlinear Manifold Clustering Algorithms

Abdolali,

Gillis

2021

Preprint

View full text Add to dashboard Cite

Subspace clustering is an important unsupervised clustering approach. It is based on the assumption that the high-dimensional data points are approximately distributed around several lowdimensional linear subspaces. The majority of the prominent subspace clustering algorithms rely on the representation of the data points as linear combinations of other data points, which is known as a self-expressive representation. To overcome the restrictive linearity assumption, numerous nonlinear approaches were proposed to extend successful subspace clustering approaches to data on a union of nonlinear manifolds. In this comparative study, we provide a comprehensive overview of nonlinear subspace clustering approaches proposed in the last decade. We introduce a new taxonomy to classify the state-of-the-art approaches into three categories, namely locality preserving, kernel based, and neural network based. The major representative algorithms within each category are extensively compared on carefully designed synthetic and real-world data sets. The detailed analysis of these approaches unfolds potential research directions and unsolved challenges in this field.

show abstract

Section: Scalable Nonlinear Sc Approachesmentioning

confidence: 99%

Beyond Linear Subspace Clustering: A Comparative Study of Nonlinear Manifold Clustering Algorithms

Abdolali,

Gillis

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The computed distance depends on the rankings of a face images pair according to each face's closest neighbours. A Deep Closed-Form Subspace Clustering (DCFSC) was introduced in [18] to learn non-linear mapping. DCFSC utilized the implicit data-driven self-expressive layer derived from closed-form shallow auto-encoder.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Face clustering is used as a preparation for manual/automatic examination of a set of pictures in surveillance systems, public security, and other applications. In many clustering scenarios [16][17][18], the labels of the face images may be provided, but most likely they are either noisy or deficient. Some face images may be incorrectly labelled.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Siamese Network for Unconstrained Face Verification and Clustering under Limited Resources

Ahmed

Hemayed

Fayek

2020

BDCC

View full text Add to dashboard Cite

In this paper, we propose an unconstrained face verification approach that is dependent on Hybrid Siamese architecture under limited resources. The general face verification trend suggests that larger training datasets and/or complex architectures lead to higher accuracy. The proposed approach tends to achieve high accuracy while using a small dataset and a simple architecture by directly learn face’s similarity/dissimilarity from raw face pixels, which is critical for various applications. The proposed architecture has two branches; the first part of these branches is trained independently, while the other parts shared their parameters. A multi-batch algorithm is utilized for training. The training process takes a few hours on a single GPU. The proposed approach achieves near-human accuracy (98.9%) on the Labeled Faces in the Wild (LFW) benchmark, which is competitive with other techniques that are presented in the literature. It reaches 99.1% on the Arabian faces dataset. Moreover, features learned by the proposed architecture are used in building a face clustering system that is based on an updated version of the Density-Based Spatial Clustering of Applications with Noise (DBSCAN). To handle the cluster quality challenge, a novel post-clustering optimization procedure is proposed. It outperforms popular clustering approaches, like K-Means and spectral by 0.098 and up to 0.344 according to F1-measure.

show abstract

“…A few variants of LRR and SSC can be found in [31], [17], [30], [36], [18]. Recently, deep learning based subspace clustering methods [11], [47], [46], [35], [13] have achieved state-of-the-art performance on many benchmark datasets. We will not detail them in this paper.…”

Section: Introductionmentioning

confidence: 99%

A Simple Approach to Automated Spectral Clustering

Fan¹,

Tu²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

The performance of spectral clustering heavily relies on the quality of affinity matrix. A variety of affinity-matrixconstruction methods have been proposed but they have hyperparameters to determine beforehand, which requires strong experience and lead to difficulty in real applications especially when the inter-cluster similarity is high or/and the dataset is large. On the other hand, we often have to determine to use a linear model or a nonlinear model, which still depends on experience. To solve these two problems, in this paper, we present an eigen-gap guided search method for subspace clustering. The main idea is to find the most reliable affinity matrix among a set of candidates constructed by linear and kernel regressions, where the reliability is quantified by the relative-eigen-gap of graph Laplacian defined in this paper. We show, theoretically and numerically, that the Laplacian matrix with a larger relative-eigen-gap often yields a higher clustering accuracy and stability. Our method is able to automatically search the best model and hyper-parameters in a pre-defined space. The search space is very easy to determine and can be arbitrarily large, though a relatively compact search space can reduce the highly unnecessary computation. Our method has high flexibility and convenience in real applications, and also has low computational cost because the affinity matrix is not computed by iterative optimization. We extend the method to large-scale datasets such as MNIST, on which the time cost is less than 90s and the clustering accuracy is state-of-the-art. Extensive experiments of natural image clustering show that our method is more stable, accurate, and efficient than baseline methods.

show abstract

Deep Closed-Form Subspace Clustering

Cited by 12 publications

References 30 publications

Beyond Linear Subspace Clustering: A Comparative Study of Nonlinear Manifold Clustering Algorithms

Beyond Linear Subspace Clustering: A Comparative Study of Nonlinear Manifold Clustering Algorithms

Hybrid Siamese Network for Unconstrained Face Verification and Clustering under Limited Resources

A Simple Approach to Automated Spectral Clustering

Contact Info

Product

Resources

About