AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations.
Guo-Jun QiLiheng ZhangChang Wen ChenQi TianPublished in: ICCV (2019)
Keyphrases
- unsupervised learning
- deep belief networks
- geometric transformations
- supervised learning
- transformation rules
- image transformations
- image segmentation
- linear transformation
- linear transformations
- intermediate representations
- deep architectures
- feature selection
- invariant representations
- rotation invariant
- higher level
- model selection
- semi supervised
- neural network
- symbolic representation
- free energy
- maximum likelihood
- multiple representations
- dimensionality reduction
- reinforcement learning
- image processing
- methods in computer vision