Deep Spectral Clustering Using Dual Autoencoder Network

By Xu Yang, Cheng Deng, Feng Zheng, Junchi Yan, Wei David Liu. 2019

288 citations recorded by the source corpus.

The clustering methods have recently absorbed even-increasing attention in learning and vision. Deep clustering combines embedding and clustering together to obtain optimal embedding subspace for clustering, which can be more effective compared with conventional clustering methods. In this paper, we propose a joint learning framework for discriminative embedding and spectral clustering. We first devise a dual autoencoder network, which enforces the reconstruction constraint for the latent representations and their noisy versions, to embed the inputs into a latent space for clustering. As such the learned latent representations can be more robust to noise. Then the mutual information estimation is utilized to provide more discriminative information from the inputs. Furthermore, a deep spectral clustering method is applied to embed the latent representations into the eigenspace and subsequently clusters them, which can fully exploit the relationship between inputs to achieve optimal clustering results. Experimental results on benchmark datasets show that our method can significantly outperform state-of-the-art clustering approaches.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Class-Incremental Instance Segmentation via Multi-Teacher Networks (2021, background): “Thanks to the development of deep learning, like other visual tasks (Wei et al. 2019; Yang et al. 2019; Han et al. 2020; Feng et al. 2020), current instance segmentation methods (He et al. 2017; Bolya et al. 2019; Chen et al. 2020) based on convolutional neural networks (CNNs) have achieved…”
Deep multi-view learning methods: A review (2021, background): “[136] propose a joint framework for discriminative embedding and spectral clustering in a dual 455 auto-encoder network.”
Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation (2020, methodology): “The weight matrix A is calculated as the nearest-neighbor graph [47], and the number of neighbors is set to 5.”
Multi-Scale Fusion Subspace Clustering Using Similarity Constraint (2020, background): “…clustering [33] has aroused widespread research interests in unsupervised learning and is successfully exploited to various applications, such as image segmentation [22, 36], motion segmentation [14, 4], image clustering [40, 5, 37, 38, 11], genes expression micro-array clustering [24] and so on.”
Deep Mixture Generative Autoencoders (2021, methodology): “In relation to classical clustering methods, VAEs have considered GMMs as prior distributions [12] and they have been used for deep spectral clustering [13], [14].”
Deep Learning for Anomaly Detection (2020, background): “A number of studies have explored this problem in recent years [25, 36, 47, 151, 162, 165, 166].”
Adversarial Fine-Grained Composition Learning for Unseen Attribute-Object Recognition (2019, background): “Generative Adversarial Network (GAN) [9] has been involved in copious amounts of computer vision and machine learning tasks [34, 32, 31] due to its promising performance.”
Self-Supervised Learning on Graphs: Contrastive, Generative, or Predictive (2021, methodology): “Inspired by various unsupervised clustering algorithms [60], [61], [62], [63], [64], [65], [66], [67], [68], if a set of clusters can be pre-obtained, the PairwiseAttrSim can be further simplified to predict the shortest path from each node to the anchor nodes associated with cluster centers, result”
Lifelong Zero-Shot Learning (2020, background): “In recent years, Zero-Shot Learning (ZSL) [Socher et al. , 2013; Xian et al. , 2018a; Zhao et al. , 2019; Wei et al. , 2019; Xu et al. , 2019] has gained increasing attention in computer vision [Chang et al. , 2020] and machine learning communities [Yang et al. , 2019].”