Improved image clustering with deep semantic embedding
Explore this paper's citation graph
Summary
This paper employed a multi-layer autoencoder based on deep neural networks (DNNs) to undertake the semantic feature embedding and dimensionality reduction, and shows that the proposed approaches can achieve superior performance over several existing clustering methods.
- Type
- article
- Published
- 2020-02-01
- Cited by
- 9
- References
- 45
- OpenAlex
- https://openalex.org/W2896473102
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:125803523
Keywords
Cluster analysis, Artificial intelligence, Pattern recognition (psychology), Computer science, Dimensionality reduction
References
- Pattern Recognition and Machine Learning
- Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Landmark Classification With Hierarchical Multi-Modal Exemplar Feature
- Clustering and projected clustering with adaptive neighbors
- Robust PCA via Outlier Pursuit
- Extracting and composing robust features with denoising autoencoders
- The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding
- Evaluation of output embeddings for fine-grained image classification
- Learning a Mahalanobis distance metric for data clustering and classification
- Content-Based Visual Landmark Search via Multimodal Hypergraph Learning
- Going deeper with convolutions
- Describing objects by their attributes
- Unsupervised feature learning for audio classification using convolutional deep belief networks
- Some methods for classification and analysis of multivariate observations
- Discriminative K-means for Clustering
- A tutorial on spectral clustering
- Learning invariant features through topographic filter maps
- Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
Cited by
- Efficient path planning of drone swarms over clustered human crowds in social events
- Collaborative Filtering Auto-Encoders for Technical Patent Recommending
- Unified embedding and clustering
- Reducing redundancy in the bottleneck representation of autoencoders
- Clustering Algorithm Based on Sparse Feature Vector without Specifying Parameter
- Semantic embedding: scene image classification using scene-specific objects
- Image Clustering Algorithm Based on Predefined Evenly-Distributed Class Centroids and Composite Cosine Distance
- A review on deep learning applications with semantics
- Unified embedding and clustering
- VAE assisted generative design optimization based on deep Gaussian processes
Related papers
- A Comparative Evaluation of AutoEncoder-Based Unsupervised Anomaly Detection Methods Applied on Space Payload
- Performance Comparison of Three Types of Autoencoder Neural Networks
- The Learning Effect of Different Hidden Layers Stacked Autoencoder
- Combining an Autoencoder and a Variational Autoencoder for Explaining the Machine Learning Model Predictions
- Assisted Diagnosis Research Based on Improved Deep Autoencoder
- From Principal Component Analysis to Autoencoders: a comparison on simulated data from psychometric models
- Manifold learning about novel continuous autoencoder network
- Using Dimensionality Reduction to Optimize t-SNE