Generalized Clustering and Multi-Manifold Learning with Geometric Structure Preservation

@article{Wu2020GeneralizedCA,
  title={Generalized Clustering and Multi-Manifold Learning with Geometric Structure Preservation},
  author={Lirong Wu and Zicheng Liu and Jun Xia and Zelin Zang and Siyuan Li and Stan Z. Li},
  journal={2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={1668-1676}
}
  • Lirong WuZicheng Liu Stan Z. Li
  • Published 21 September 2020
  • Computer Science
  • 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Though manifold-based clustering has become a popular research topic, we observe that one important factor has been omitted by these works, namely that the defined clustering loss may corrupt the local and global structure of the latent space. In this paper, we propose a novel Generalized Clustering and Multi-manifold Learning (GCML) framework with geometric structure preservation for generalized data, i.e., not limited to 2-D image data and has a wide range of applications in speech, text, and… 

Figures and Tables from this paper

Preserving Data Manifold Structure in Latent Space for Exploration through Network Geodesics

An Encoded Prior Sliced Wasserstein AutoEncoder wherein an additional prior-encoder network learns a geometry and topology preserving embedding of any data manifold, thus improving the structure of latent space.

Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation

This paper proposes a novel multi-teacher knowledge distillation framework for Automated Graph Self-Supervised Learning ( AGSSL), which consists of two main branches: Knowledge Extraction and Knowledge Integration.

References

SHOWING 1-10 OF 29 REFERENCES

Improved Deep Embedded Clustering with Local Structure Preservation

The Improved Deep Embedded Clustering (IDEC) algorithm is proposed, which manipulates feature space to scatter data points using a clustering loss as guidance and can jointly optimize cluster labels assignment and learn features that are suitable for clustering with local structure preservation.

Multi-manifold Discriminant Isomap for visualization and classification

Semi-supervised local multi-manifold Isomap by linear embedding for feature extraction

N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding

This work quantitatively shows across a range of image and time-series datasets that the proposed method has competitive performance against the latest deep clustering algorithms, including outperforming current state-of-the-art on several.

Deep Spectral Clustering Using Dual Autoencoder Network

A joint learning framework for discriminative embedding and spectral clustering is proposed, which can significantly outperform state-of-the-art clustering approaches and be more robust to noise.

Consistent Representation Learning for High Dimensional Data Analysis

Extensive comparative results show that the proposed CRL neural network method outperforms the popular t-SNE and UMAP-based and other contemporary clustering and visualization algorithms in terms of evaluation metrics and visualization.

ClusterGAN : Latent Space Clustering in Generative Adversarial Networks

The results show a remarkable phenomenon that GANs can preserve latent space interpolation across categories, even though the discriminator is never exposed to such vectors.

Learning Deep Representations for Graph Clustering

This work proposes a simple method, which first learns a nonlinear embedding of the original graph by stacked autoencoder, and then runs $k$-means algorithm on the embedding to obtain the clustering result, which significantly outperforms conventional spectral clustering.

Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering

Variational Deep Embedding (VaDE) is proposed, a novel unsupervised generative clustering approach within the framework of Variational Auto-Encoder (VAE), which shows its capability of generating highly realistic samples for any specified cluster, without using supervised information during training.

SpectralNet: Spectral Clustering using Deep Neural Networks

A deep learning approach to spectral clustering that overcomes the major limitations of scalability and generalization of the spectral embedding and applies VC dimension theory to derive a lower bound on the size of SpectralNet.