DeepAI AI Chat
Log In Sign Up

The magnitude vector of images

by   Michael F Adamer, et al.

The magnitude of a finite metric space is a recently-introduced invariant quantity. Despite beneficial theoretical and practical properties, such as a general utility for outlier detection, and a close connection to Laplace radial basis kernels, magnitude has received little attention by the machine learning community so far. In this work, we investigate the properties of magnitude on individual images, with each image forming its own metric space. We show that the known properties of outlier detection translate to edge detection in images and we give supporting theoretical justifications. In addition, we provide a proof of concept of its utility by using a novel magnitude layer to defend against adversarial attacks. Since naive magnitude calculations may be computationally prohibitive, we introduce an algorithm that leverages the regular structure of images to dramatically reduce the computational cost.


page 4

page 8

page 12

page 13

page 14

page 15


Practical applications of metric space magnitude and weighting vectors

Metric space magnitude, an active subject of research in algebraic topol...

Weighting vectors for machine learning: numerical harmonic analysis applied to boundary detection

Metric space magnitude, an active field of research in algebraic topolog...

Metric Space Magnitude and Generalisation in Neural Networks

Deep learning models have seen significant successes in numerous applica...

Automatic identification of outliers in Hubble Space Telescope galaxy images

Rare extragalactic objects can carry substantial information about the p...

Integrating Network Embedding and Community Outlier Detection via Multiclass Graph Description

Network (or graph) embedding is the task to map the nodes of a graph to ...

Outliers Dimensions that Disrupt Transformers Are Driven by Frequency

Transformer-based language models are known to display anisotropic behav...

Magnitude and topological entropy of digraphs

Magnitude and (co)weightings are quite general constructions in enriched...