EscherNet 101

03/07/2023

∙

A deep learning model, EscherNet 101, is constructed to categorize images of 2D periodic patterns into their respective 17 wallpaper groups. Beyond evaluating EscherNet 101 performance by classification rates, at a micro-level we investigate the filters learned at different layers in the network, capable of capturing second-order invariants beyond edge and curvature.

READ FULL TEXT

EscherNet 101

ISAAC Newton: Input-based Approximate Curvature for Newton's Method

PSNet: a deep learning model based digital phase shifting algorithm from a single fringe image

A Discrete Scheme for Computing Image's Weighted Gaussian Curvature

A Monotone, Second Order Accurate Scheme for Curvature Motion

On Explicit Curvature Regularization in Deep Generative Models

Is Fast Adaptation All You Need?

On the Importance of Capturing a Sufficient Diversity of Perspective for the Classification of micro-PCBs

EscherNet 101

Related Research

ISAAC Newton: Input-based Approximate Curvature for Newton's Method

PSNet: a deep learning model based digital phase shifting algorithm from a single fringe image

A Discrete Scheme for Computing Image's Weighted Gaussian Curvature

A Monotone, Second Order Accurate Scheme for Curvature Motion

On Explicit Curvature Regularization in Deep Generative Models

Is Fast Adaptation All You Need?

On the Importance of Capturing a Sufficient Diversity of Perspective for the Classification of micro-PCBs