Augmenting Features via Contrastive Learning-based Generative Model for Long-Tailed Classification.
Minho ParkHyung-Il KimHwa Jeon SongDong-oh KangPublished in: ICCV (Workshops) (2023)
Keyphrases
- generative model
- discriminative learning
- prior knowledge
- feature representations
- learned models
- feature representation
- classification accuracy
- feature space
- feature vectors
- supervised learning
- boltzmann machine
- learning algorithm
- feature extraction
- machine learning
- classification models
- image classification
- unsupervised learning
- discriminative models
- feature set
- probabilistic model
- text classification
- data sets
- class labels
- conditional random fields
- learning tasks
- semi supervised
- learning phase
- image features
- generative and discriminative models
- computer vision
- dictionary learning
- bayesian framework
- action recognition
- model selection