Pattern recognition (psychology)

Mathematics

Economic growth

Algorithm

Image (mathematics)

Mathematical analysis

Artificial intelligence

Economics

Generalization

Programming language

Class (philosophy)

Convergence (economics)

SIGNAL (programming language)

Computer science

Computer vision

Artificial neural network

Coordinate system

Coordinate-based neural representations have shown significant promise as an alternative to discrete, array-based representations for complex low dimensional signals. However, optimizing a coordinate-based network from randomly initialized weights for each new signal is inefficient. We propose applying standard meta-learning algorithms to learn the initial weight parameters for these fully-connected networks based on the underlying class of signals being represented (e.g., images of faces or 3D models of chairs). Despite requiring only a minor change in implementation, using these learned initial weights enables faster convergence during optimization and can serve as a strong prior over the signal class being modeled, resulting in better generalization when only partial observations of a given signal are available. We explore these benefits across a variety of tasks, including representing 2D images, reconstructing CT scans, and recovering 3D shapes and scenes from 2D image observations.

Learned Initializations for Optimizing Coordinate-Based Neural Representations