A Dipole Imaging Method Based on Azimuthal Equidistant Projection

Li, Mingai; Liu, Bin; Ruan, Zi-wei

doi:10.1109/icaa53760.2021.00137

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a standard type of projection which falls under the category of azimuthal projections [Close, 1921] with wide applications in fields such as cartography [Snyder, 1997] and mathematics [Li et al, 2021]. In this projection, there are two control points, and projection is performed such that distance of all points from the two control points is preserved.…”

Section: A Two-point Equidistant Projectionmentioning

confidence: 99%

Decision boundaries and convex hulls in the feature space that deep learning functions learn from images

Yousefzadeh¹

2022

Preprint

View full text Add to dashboard Cite

The success of deep neural networks in image classification and learning can be partly attributed to the features they extract from images. It is often speculated about the properties of a low-dimensional manifold that models extract and learn from images. However, there is not sufficient understanding about this low-dimensional space based on theory or empirical evidence. For image classification models, their last hidden layer is the one where images of each class is separated from other classes and it also has the least number of features. Here, we develop methods and formulations to study that feature space for any model. We study the partitioning of the domain in feature space, identify regions guaranteed to have certain classifications, and investigate its implications for the pixel space. We observe that geometric arrangements of decision boundaries in feature space is significantly different compared to pixel space, providing insights about adversarial vulnerabilities, image morphing, extrapolation, ambiguity in classification, and the mathematical understanding of image classification models.

show abstract

Section: A Two-point Equidistant Projectionmentioning

confidence: 99%