Graph Convolutional Networks based on Manifold Learning for Semi-Supervised Image Classification.
Lucas Pascotti ValemDaniel Carlos Guimarães PedronetteLongin Jan LateckiPublished in: CoRR (2023)
Keyphrases
- manifold learning
- semi supervised
- image classification
- neighborhood graph
- graph construction
- label propagation
- feature extraction
- sparse coding
- semi supervised learning
- subspace learning
- sparse representation
- labeled data
- low dimensional
- nonlinear dimensionality reduction
- diffusion maps
- unsupervised learning
- graph embedding
- dimensionality reduction
- pairwise
- image representation
- supervised learning
- active learning
- bag of words
- metric learning
- pairwise constraints
- high dimensional
- random walk
- geodesic distance
- manifold structure
- data sets
- unlabeled data
- generative model
- weighted graph
- dimension reduction
- visual words
- high dimensional data
- kernel machines
- laplacian eigenmaps
- feature vectors
- preprocessing
- graph laplacian
- manifold embedding
- locally linear embedding
- pattern recognition
- machine learning