Estimating Shape Distances on Neural Representations with Limited Samples.
Dean A. PospisilBrett W. LarsenSarah E. HarveyAlex H. WilliamsPublished in: CoRR (2023)
Keyphrases
- dissimilarity measure
- sample points
- shape descriptors
- shape analysis
- neural network
- distributed representations
- shape properties
- data sets
- network architecture
- distance map
- shape representation
- distance measure
- hausdorff distance
- probabilistic principal component analysis
- shape model
- rigid body
- geodesic distance
- bio inspired
- learning rules
- euclidean space
- topological features
- geometrical properties
- method assumes
- higher level
- single image
- statistical shape model
- feature space
- similarity measure
- computer vision
- learning algorithm
- object shapes
- euclidean distance