Sparse coding with invariance constraints

Authors:
Heiko Wersing;Julian Eggert;Edgar Körner
Affiliations:
HONDA Research Institute Europe GmbH, Offenbach/Main, Germany;HONDA Research Institute Europe GmbH, Offenbach/Main, Germany;HONDA Research Institute Europe GmbH, Offenbach/Main, Germany
Venue:
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Year:
2003

Citing 3
Cited 2

Lyapunov functions for neural nets with nondifferentiable input-output characteristics

Neural Computation
A Competitive-Layer Model for Feature Binding and Sensory Segmentation

Neural Computation
Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces

Neural Computation

Fields of Experts

International Journal of Computer Vision
Sparse image representations with shift-invariant tree-structured dictionaries

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

We suggest a new approach to optimize the learning of sparse features under the constraints of explicit transformation symmetries imposed on the set of feature vectors. Given a set of basis feature vectors and invariance transformations, from each basis feature a family of transformed features is generated. We then optimize the basis features for optimal sparse reconstruction of the input pattern ensemble using the whole transformed feature family. If the predefined transformation invariance coincides with an invariance in the input data, we obtain a less redundant basis feature set, compared to sparse coding approaches without invariances.We demonstrate the application to a test scenario of overlapping bars and the learning of receptive fields in hierarchical visual cortex models.