Unsupervised Learning Framework of Interest Point Via Properties Optimization

Understand

This paper presents an entirely unsupervised interest point training framework by jointly learning detector and descriptor, which takes an image as input and outputs a probability and a description for every image point.

• The objective of the training framework is formulated as joint probability distribution of the properties of the extracted points.
• The essential properties are selected as sparsity, repeatability and discriminability which are formulated by the probabilities.
• To maximize the objective efficiently, latent variable is introduced to represent the probability of that a point satisfies the required properties.