MIX'EM: Unsupervised Image Classification Using a Mixture of Embeddings.
Ali VarameshTinne TuytelaarsPublished in: ACCV (3) (2020)
Keyphrases
- image classification
- expectation maximization
- finite mixture model
- mixture model
- unsupervised learning
- em algorithm
- image representation
- gaussian mixture model
- gaussian distribution
- maximum likelihood
- probabilistic model
- density estimation
- gaussian mixture
- parameter estimation
- bag of words
- vector space
- visual words
- visual features
- image features
- feature extraction
- supervised learning
- dimensionality reduction
- gaussian densities
- supervised classification
- unsupervised manner
- mixture of gaussians
- image segmentation
- sparse coding
- generative model
- data driven
- semi supervised
- manifold learning
- multi label
- sparse representation
- low dimensional
- image processing
- bag of features
- class specific
- expectation maximisation
- distance measure
- dirichlet distribution
- unsupervised methods