4 papers · 1 filter
Learning Infinitesimal Generators of Continuous Symmetries from Data
Gyeonghoon Ko, Hyunsu Kim, Juho Lee
Exploiting symmetry inherent in data can significantly improve the sample efficiency of a learning procedure and the generalization of learned models. When data clearly reveals und…
Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts
Hyunsu Kim, Yegon Kim, Hongseok Yang +1
Group Equivariant CNNs (G-CNNs) have shown promising efficacy in various tasks, owing to their ability to capture hierarchical features in an equivariant manner. However, their equ…
Fast Ensembling with Diffusion Schrödinger Bridge
Hyunsu Kim, Jongmin Yoon, Juho Lee
Deep Ensemble (DE) approach is a straightforward technique used to enhance the performance of deep neural networks by training them from different initial points, converging toward…
Sequential Flow Straightening for Generative Modeling
Jongmin Yoon, Juho Lee
Straightening the probability flow of the continuous-time generative models, such as diffusion models or flow-based models, is the key to fast sampling through the numerical solver…