1 code implementation • 23 Jun 2023 • Kion Fallah, Alec Helbling, Kyle A. Johnsen, Christopher J. Rozell
In this work, we propose a contrastive learning approach that directly models the latent manifold using Lie group operators parameterized by coefficients with a sparsity-promoting prior.
1 code implementation • 1 Apr 2023 • Alec Helbling, Christopher J. Rozell, Matthew O'Shaughnessy, Kion Fallah
Using information from a sequence of query responses, we can estimate user preferences over a set of image attributes and perform preference-guided image editing and generation.
no code implementations • 26 Jul 2022 • Christoffer Loeffler, Kion Fallah, Stefano Fenu, Dario Zanca, Bjoern Eskofier, Christopher John Rozell, Christopher Mutschler
We adapt an entropy-based active learning method with recent work from triplet mining to collect easy-to-answer but still informative annotations from human participants and use them to train a deep convolutional network that generalizes to unseen samples.
2 code implementations • 7 May 2022 • Kion Fallah, Christopher J. Rozell
Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure.
1 code implementation • 28 Apr 2022 • Alec Helbling, Christopher John Rozell, Matthew O'Shaughnessy, Kion Fallah
Isolating and controlling specific features in the outputs of generative models in a user-friendly way is a difficult and open-ended problem.
1 code implementation • 22 Jun 2021 • Marissa Connor, Kion Fallah, Christopher Rozell
However, these approaches are limited because they require transformation labels when training their models and they lack a method for determining which regions of the manifold are appropriate for applying each specific operator.
1 code implementation • NeurIPS 2020 • Kion Fallah, Adam Willats, Ninghao Liu, Christopher Rozell
Unfortunately, current proposals for sparse coding in the compressed space require a centralized compression process (i. e., dense random matrix) that is biologically unrealistic due to local wiring constraints observed in neural circuits.