Deep Adversarial Subspace Clustering

Zhou, Pan; Hou, Yunqing; Feng, Jiashi

doi:10.1109/cvpr.2018.00172

Cited by 158 publications

(95 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While promising clustering accuracy has been reported, these methods are still suboptimal because neither the potentially useful supervision information from the clustering result has been taken into the feature learning step nor a joint optimization framework for fully combining feature learning and subspace clustering has been developed. More recently, in [54], a deep adversarial network with a subspace-specific generator and a subspace-specific discriminator is adopted in the framework of [14] for subspace clustering. However, the discriminator need to use the dimension of each subspace, which is usually unknown.…”

Section: Subspace Clustering In Feature Spacementioning

confidence: 99%

Self-Supervised Convolutional Subspace Clustering Network

Zhang

You

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

144

View full text Add to dashboard Cite

Subspace clustering methods based on data selfexpression have become very popular for learning from data that lie in a union of low-dimensional linear subspaces. However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces. On the other hand, while Convolutional Neural Network (ConvNet) has been demonstrated to be a powerful tool for extracting discriminative features from visual data, training such a ConvNet usually requires a large amount of labeled data, which are unavailable in subspace clustering applications. To achieve simultaneous feature learning and subspace clustering, we propose an end-to-end trainable framework, called Self-Supervised Convolutional Subspace Clustering Network (S 2 ConvSCN), that combines a ConvNet module (for feature learning), a self-expression module (for subspace clustering) and a spectral clustering module (for selfsupervision) into a joint optimization framework. Particularly, we introduce a dual self-supervision that exploits the output of spectral clustering to supervise the training of the feature learning module (via a classification loss) and the self-expression module (via a spectral clustering loss). Our experiments on four benchmark datasets show the effectiveness of the dual self-supervision and demonstrate superior performance of our proposed approach.

show abstract

Section: Subspace Clustering In Feature Spacementioning

confidence: 99%

Self-Supervised Convolutional Subspace Clustering Network

Zhang

You

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

144

View full text Add to dashboard Cite

show abstract

“…It is also noteworthy that performance of the DCFSC in this experiment was reported to be comparable with 26.6%, which was reported in the study [37] combining more sophisticated methodologies such as self-supervised learning with the DSC. Since DCFSC is easy to combine with the more advanced models [41,37,40,39] of DSC, there is possibility of further enhancing the performance of these modified models with deeper neural architecture. 3…”

Section: Resultsmentioning

confidence: 99%

“…Our DCFSC has advantages in methodological simplicity and memory efficiency compared to DSC. 3 It is also remarkable that in 'Deep Adversarial Subspace Clustering' paper [41] the proposed model could not be used to try experiment in COIL-100, even with a very shallow auto-encoder model. It was also due to a memory shortage problem.…”

Section: Discussionmentioning

confidence: 99%

“…The biggest contribution of [12] was that they firstly designed the self-expressive layer and corresponding loss function which models self-expressiveness property of data into deep auto-encoder. Since DSC showed great performance on various benchmarks, there have been many subsequent studies [41,37,40,39] that tried to improve the DSC in several aspects. Deep adversarial subspace clustering [41] exploited GAN-like adversarial learning framework to supervise sample representation learning and subspace clustering.…”

Section: Related Workmentioning

confidence: 99%

“…Since DSC showed great performance on various benchmarks, there have been many subsequent studies [41,37,40,39] that tried to improve the DSC in several aspects. Deep adversarial subspace clustering [41] exploited GAN-like adversarial learning framework to supervise sample representation learning and subspace clustering. [37] proposed a dual selfsupervision framework which exploited the output of spectral clustering to supervise the training of the feature learning module and the self-expression module.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Deep Closed-Form Subspace Clustering

Seo¹,

Koo²,

Jeon³

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

We propose Deep Closed-Form Subspace Clustering (DCFSC), a new embarrassingly simple model for subspace clustering with learning non-linear mapping. Compared with the previous deep subspace clustering (DSC) techniques, our DCFSC does not have any parameters at all for the self-expressive layer. Instead, DCFSC utilizes the implicit data-driven self-expressive layer derived from closed-form shallow auto-encoder. Moreover, DCFSC also has no complicated optimization scheme, unlike the other subspace clustering methods. With its extreme simplicity, DCFSC has significant memory-related benefits over the existing DSC method, especially on the large dataset. Several experiments showed that our DCFSC model had enough potential to be a new reference model for subspace clustering on large-scale high-dimensional dataset.

show abstract

GATCluster: Self-supervised Gaussian-Attention Network for Image Clustering

Niu

Zhang

Wang

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Deep clustering has achieved state-of-the-art results via joint representation learning and clustering, but still has an inferior performance for the real scene images, e.g., those in ImageNet. With such images, deep clustering methods face several challenges, including extracting discriminative features, avoiding trivial solutions, capturing semantic information, and performing on large-size image datasets. To address these problems, here we propose a self-supervised attention network for image clustering (AttentionCluster). Rather than extracting intermediate features first and then performing the traditional clustering algorithm, AttentionCluster directly outputs semantic cluster labels that are more discriminative than intermediate features and does not need further post-processing. To train the AttentionCluster in a completely unsupervised manner, we design four learning tasks with the constraints of transformation invariance, separability maximization, entropy analysis, and attention mapping. Specifically, the transformation invariance and separability maximization tasks learn the relationships between sample pairs. The entropy analysis task aims to avoid trivial solutions. To capture the object-oriented semantics, we design a self-supervised attention mechanism that includes a parameterized attention module and a soft-attention loss. All the guiding signals for clustering are self-generated during the training process. Moreover, we develop a two-step learning algorithm that is training-friendly and memory-efficient for processing large-size images. Extensive experiments demonstrate the superiority of our proposed method in comparison with the state-of-the-art image clustering benchmarks.

show abstract

Deep Adversarial Subspace Clustering

Cited by 158 publications

References 19 publications

Self-Supervised Convolutional Subspace Clustering Network

Self-Supervised Convolutional Subspace Clustering Network

Deep Closed-Form Subspace Clustering

GATCluster: Self-supervised Gaussian-Attention Network for Image Clustering

Contact Info

Product

Resources

About