Alert button
Picture for Henry Kvinge

Henry Kvinge

Alert button

Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps

Oct 13, 2021
Nico Courts, Henry Kvinge

Figure 1 for Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
Figure 2 for Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
Figure 3 for Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
Figure 4 for Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
Viaarxiv icon

A Topological-Framework to Improve Analysis of Machine Learning Model Performance

Jul 09, 2021
Henry Kvinge, Colby Wight, Sarah Akers, Scott Howland, Woongjo Choi, Xiaolong Ma, Luke Gosink, Elizabeth Jurrus, Keerti Kappagantula, Tegan H. Emerson

Figure 1 for A Topological-Framework to Improve Analysis of Machine Learning Model Performance
Figure 2 for A Topological-Framework to Improve Analysis of Machine Learning Model Performance
Viaarxiv icon

Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions

Jun 07, 2021
Scott Mahan, Henry Kvinge, Tim Doster

Figure 1 for Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions
Figure 2 for Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions
Figure 3 for Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions
Figure 4 for Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions
Viaarxiv icon

One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations

Jun 02, 2021
Henry Kvinge, Scott Howland, Nico Courts, Lauren A. Phillips, John Buckheit, Zachary New, Elliott Skomski, Jung H. Lee, Sandeep Tiwari, Jessica Hibler, Courtney D. Corley, Nathan O. Hodas

Figure 1 for One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
Figure 2 for One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
Figure 3 for One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
Figure 4 for One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
Viaarxiv icon

Sheaves as a Framework for Understanding and Interpreting Model Fit

May 21, 2021
Henry Kvinge, Brett Jefferson, Cliff Joslyn, Emilie Purvine

Figure 1 for Sheaves as a Framework for Understanding and Interpreting Model Fit
Figure 2 for Sheaves as a Framework for Understanding and Interpreting Model Fit
Figure 3 for Sheaves as a Framework for Understanding and Interpreting Model Fit
Figure 4 for Sheaves as a Framework for Understanding and Interpreting Model Fit
Viaarxiv icon

Prototypical Region Proposal Networks for Few-Shot Localization and Classification

Apr 08, 2021
Elliott Skomski, Aaron Tuor, Andrew Avila, Lauren Phillips, Zachary New, Henry Kvinge, Courtney D. Corley, Nathan Hodas

Figure 1 for Prototypical Region Proposal Networks for Few-Shot Localization and Classification
Figure 2 for Prototypical Region Proposal Networks for Few-Shot Localization and Classification
Figure 3 for Prototypical Region Proposal Networks for Few-Shot Localization and Classification
Viaarxiv icon

Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning

Sep 23, 2020
Henry Kvinge, Zachary New, Nico Courts, Jung H. Lee, Lauren A. Phillips, Courtney D. Corley, Aaron Tuor, Andrew Avila, Nathan O. Hodas

Figure 1 for Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
Figure 2 for Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
Figure 3 for Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
Figure 4 for Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
Viaarxiv icon

More chemical detection through less sampling: amplifying chemical signals in hyperspectral data cubes through compressive sensing

Jun 27, 2019
Henry Kvinge, Elin Farnell, Julia R. Dupuis, Michael Kirby, Chris Peterson, Elizabeth C. Schundler

Figure 1 for More chemical detection through less sampling: amplifying chemical signals in hyperspectral data cubes through compressive sensing
Figure 2 for More chemical detection through less sampling: amplifying chemical signals in hyperspectral data cubes through compressive sensing
Figure 3 for More chemical detection through less sampling: amplifying chemical signals in hyperspectral data cubes through compressive sensing
Figure 4 for More chemical detection through less sampling: amplifying chemical signals in hyperspectral data cubes through compressive sensing
Viaarxiv icon

A data-driven approach to sampling matrix selection for compressive sensing

Jun 20, 2019
Elin Farnell, Henry Kvinge, John P. Dixon, Julia R. Dupuis, Michael Kirby, Chris Peterson, Elizabeth C. Schundler, Christian W. Smith

Figure 1 for A data-driven approach to sampling matrix selection for compressive sensing
Figure 2 for A data-driven approach to sampling matrix selection for compressive sensing
Figure 3 for A data-driven approach to sampling matrix selection for compressive sensing
Figure 4 for A data-driven approach to sampling matrix selection for compressive sensing
Viaarxiv icon

Rare geometries: revealing rare categories via dimension-driven statistics

Jan 29, 2019
Henry Kvinge, Elin Farnell

Figure 1 for Rare geometries: revealing rare categories via dimension-driven statistics
Figure 2 for Rare geometries: revealing rare categories via dimension-driven statistics
Figure 3 for Rare geometries: revealing rare categories via dimension-driven statistics
Figure 4 for Rare geometries: revealing rare categories via dimension-driven statistics
Viaarxiv icon