Unsupervised Deep Embedding for Clustering Analysis
Explore this paper's citation graph
Summary
Deep Embedded Clustering is proposed, a method that simultaneously learns feature representations and cluster assignments using deep neural networks and learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective.
- Type
- preprint
- Published
- 2015-11-19
- Cited by
- 3,560
- References
- 42
- Access
- Open access
- OpenAlex
- https://openalex.org/W2173649752
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:6779105
Keywords
Cluster analysis, Computer science, Artificial intelligence, Embedding, Feature (linguistics)
References
- Pattern Recognition and Machine Learning
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Accelerating t-SNE using tree-based algorithms
- Fully convolutional networks for semantic segmentation
- Entropy-based criterion in categorical clustering
- Approximation capabilities of multilayer feedforward networks
- Analyzing the effectiveness and applicability of co-training
- What makes Paris look like Paris?
- Learning a Mahalanobis distance metric for data clustering and classification
- Dropout: a simple way to prevent neural networks from overfitting
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Toward integrating feature selection algorithms for classification and clustering
- Gradient-based learning applied to document recognition
- Learning a Parametric Embedding by Preserving Local Structure
- Distance Metric Learning with Application to Clustering with Side-Information
- Building high-level features using large scale unsupervised learning
- Some methods for classification and analysis of multivariate observations
- On Clustering Validation Techniques
- Image Clustering Using Local Discriminant Models and Global Integration
- Spectral Embedded Clustering: A Framework for In-Sample and Out-of-Sample Spectral Clustering
Cited by
- Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding
- Neural network-based clustering using pairwise constraints
- Cloud Computing and Security
- Semi-Supervised Representation Learning based on Probabilistic Labeling
- Deep learning prototype domains for person re-identification
- Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
- Machine Learning using Principal Manifolds and Mode Seeking
- Variational Deep Embedding: A Generative Approach to Clustering
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Deep Image Category Discovery using a Transferred Similarity Function
- Domain Ontology Induction Using Word Embeddings
- Generative mixture of networks
- Learning Discrete Representations via Information Maximizing Self-Augmented Training
- Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
- Cascade Subspace Clustering
- Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
- Semantic Autoencoder for Zero-Shot Learning
- Spatio-Temporal Anomaly Detection for Industrial Robots through Prediction in Unsupervised Feature Space
- Human-like Clustering with Deep Convolutional Neural Networks
- Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
Related papers
- Gradient-based learning applied to document recognition
- Visualizing Data using t-SNE
- Improved Deep Embedded Clustering with Local Structure Preservation
- Deep Residual Learning for Image Recognition
- Deep Embedding Network for Clustering
- Reducing the Dimensionality of Data with Neural Networks
- Improving Spectral Clustering with Deep Embedding and Cluster Estimation