Haldane Bundles: A Dataset for Learning to Predict the Chern Number of Line Bundles on the Torus

1 code implementation • 6 Dec 2023 • Cody Tipton, Elizabeth Coda, Davis Brown, Alyson Bittner, Jung Lee, Grayson Jorgenson, Tegan Emerson, Henry Kvinge

Characteristic classes, which are abstract topological invariants associated with vector bundles, have become an important notion in modern physics with surprising real-world consequences.

ColMix -- A Simple Data Augmentation Framework to Improve Object Detector Performance and Robustness in Aerial Images

no code implementations • 22 May 2023 • Cuong Ly, Grayson Jorgenson, Dan Rosa de Jesus, Henry Kvinge, Adam Attarian, Yijing Watkins

In this work, we present a novel augmentation method, called collage pasting, for increasing the object density without a need for segmentation masks, thereby improving the detector performance.

Data Augmentation Object

Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds

no code implementations • 19 Nov 2022 • Henry Kvinge, Grayson Jorgenson, Davis Brown, Charles Godfrey, Tegan Emerson

While the last five years have seen considerable progress in understanding the internal representations of deep learning models, many questions remain.

In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?

no code implementations • 7 Oct 2022 • Henry Kvinge, Tegan H. Emerson, Grayson Jorgenson, Scott Vasquez, Timothy Doster, Jesse D. Lew

It is often said that a deep learning model is "invariant" to some specific type of transformation.

Data Augmentation

Testing predictions of representation cost theory with CNNs

1 code implementation • 3 Oct 2022 • Charles Godfrey, Elise Bishoff, Myles Mckay, Davis Brown, Grayson Jorgenson, Henry Kvinge, Eleanor Byler

It is widely acknowledged that trained convolutional neural networks (CNNs) have different levels of sensitivity to signals of different frequency.