Structured AutoEncoders for Subspace Clustering

By Xi Peng, Jiashi Feng, Shijie Xiao, Wei Yun Yau, Joey Tianyi Zhou, Songfan Yang. IEEE Transactions on Image Processing, 2018

326 citations recorded by the source corpus.

Existing subspace clustering methods typically employ shallow models to estimate underlying subspaces of unlabeled data points and cluster them into corresponding groups. However, due to the limited representative capacity of the employed shallow models, those methods may fail in handling realistic data without the linear subspace structure. To address this issue, we propose a novel subspace clustering approach by introducing a new deep model—Structured AutoEncoder (StructAE). The StructAE learns a set of explicit transformations to progressively map input data points into nonlinear latent spaces while preserving the local and global subspace structure. In particular, to preserve local structure, the StructAE learns representations for each data point by minimizing reconstruction error with respect to itself. To preserve global structure, the StructAE incorporates a prior structured information by encouraging the learned representation to preserve specified reconstruction patterns over the entire data set. To the best of our knowledge, StructAE is one of the first deep subspace clustering approaches. Extensive experiments show that the proposed StructAE significantly outperforms 15 state-of-the-art subspace clustering approaches in terms of five evaluation metrics.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1dd0ca83df9ab52261ba34a74e737565262dff47

How researchers see this paper

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

In Artificial Intelligence

1. Jiancheng Lv
2. En Zhu
3. Cheng Deng
4. Xinwang Liu
5. Xi Peng
6. Pei Zhang
7. Xu Yang
8. Joey Tianyi Zhou

In Computer Vision and Pattern Recognition

1. Cheng Deng
2. En Zhu
3. Xu Yang
4. Jiancheng Lv
5. Xinwang Liu
6. Pei Zhang
7. Xi Peng
8. Xinzhong Zhu

In Signal Processing

1. Joey Tianyi Zhou
2. Xi Peng
3. Feiping Nie
4. Cheng Deng
5. Yuanbiao Gou
6. Jiancheng Lv
7. Yijie Lin
8. Xu Yang

Citations in the corpus

• Structured Graph Learning for Scalable Subspace Clustering: From Single View to Multiview (2021, unknown): “3061660 finding relevant dimensions spanning a subspace for each cluster [6], [7].”
• Scalable Deep Multimodal Learning for Cross-Modal Retrieval (2019, background): “Over the past several years, the deep neural network (DNN) has achieved great success in many applications, such as image classification, object detection, and clustering [23, 46].”
• COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction (2021, methodology): “After that, the common representation, which is obtained by simply concatenating all view-specific representations together, is further fed into k-means to get the clustering results like the traditional fashion [1, 10, 22, 25, 26, 32, 39, 42, 43, 48, 49, 53].”
• AnomalyNet: An Anomaly Detection Network for Video Surveillance (2019, unknown): “To embrace the data-driven feature learning [31], [32], recent attention has shifted from feature engineering to deep neural networks.”
• COMIC: Multi-view Clustering Without Parameter Selection (2019, background): “…2019 by the author(s). source (Hocking et al., 2011; Elhamifar & Vidal, 2013; Liu et al., 2016; Flammarion et al., 2017; Shah & Koltun, 2017; Liu et al., 2019; Peng et al., 2017a; 2018; Liu et al., 2017), which may be less attractive to some scenarios due to the heterogeneous properties in data.”
• Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance (2021, background): “Recently, to improve the efficiency of subspace algorithms, anchor graph strategy has been proposed to select landmarks to represent the entire data items [8], [12], [19]–[23].”
• Saliency Detection via a Multiple Self-Weighted Graph-Based Manifold Ranking (2020, background): “Recently, deep learning has shown significant performance for many computer vision tasks [25], [26] which also makes significant gains in saliency detection.”