DeepAI AI Chat
Log In Sign Up

Learning Smooth Pattern Transformation Manifolds

by   Elif Vural, et al.

Manifold models provide low-dimensional representations that are useful for processing and analyzing data in a transformation-invariant way. In this paper, we study the problem of learning smooth pattern transformation manifolds from image sets that represent observations of geometrically transformed signals. In order to construct a manifold, we build a representative pattern whose transformations accurately fit various input images. We examine two objectives of the manifold building problem, namely, approximation and classification. For the approximation problem, we propose a greedy method that constructs a representative pattern by selecting analytic atoms from a continuous dictionary manifold. We present a DC (Difference-of-Convex) optimization scheme that is applicable to a wide range of transformation and dictionary models, and demonstrate its application to transformation manifolds generated by rotation, translation and anisotropic scaling of a reference pattern. Then, we generalize this approach to a setting with multiple transformation manifolds, where each manifold represents a different class of signals. We present an iterative multiple manifold building algorithm such that the classification accuracy is promoted in the learning of the representative patterns. Experimental results suggest that the proposed methods yield high accuracy in the approximation and classification of data compared to some reference methods, while the invariance to geometric transformations is achieved due to the transformation manifold model.


page 7

page 8

page 13


Discretization of Parametrizable Signal Manifolds

Transformation-invariant analysis of signals often requires the computat...

Learning Invariances with Generalised Input-Convex Neural Networks

Considering smooth mappings from input vectors to continuous targets, ou...

Learning Identity-Preserving Transformations on Data Manifolds

Many machine learning techniques incorporate identity-preserving transfo...

Graph-based classification of multiple observation sets

We consider the problem of classification of an object given multiple ob...

A Study of Image Analysis with Tangent Distance

The computation of the geometric transformation between a reference and ...

Unsupervised Co-Learning on G-Manifolds Across Irreducible Representations

We introduce a novel co-learning paradigm for manifolds naturally equipp...

Masking Strategies for Image Manifolds

We consider the problem of selecting an optimal mask for an image manifo...