1 code implementation • 26 Oct 2023 • Yonghyeon LEE
Motion Manifold Primitives (MMP), a manifold-based approach for encoding basic motion skills, can produce diverse trajectories, enabling the system to adapt to unseen constraints.
no code implementations • 19 Sep 2023 • Yonghyeon LEE, Frank Chongwoo Park
We propose a family of curvature-based regularization terms for deep generative model learning.
no code implementations • 15 Sep 2023 • Yonghyeon LEE
Given a set of high-dimensional data points that approximately lie on some lower-dimensional manifold, an autoencoder learns the \textit{manifold} and its \textit{coordinate chart}, simultaneously.
1 code implementation • 20 Aug 2022 • Sangwoong Yoon, Jinwon Choi, Yonghyeon LEE, Yung-Kyun Noh, Frank Chongwoo Park
A reliable evaluation method is essential for building a robust out-of-distribution (OOD) detector.
1 code implementation • NeurIPS 2021 • Yonghyeon LEE, Hyeokjun Kwon, Frank Park
Unlike existing graph-based methods that attempt to encode the training data to some prescribed latent space distribution -- one consequence being that only the encoder is the object of the regularization -- NRAE merges local connectivity information contained in the neighborhood graphs with local quadratic approximations of the decoder function to formulate a new neighborhood reconstruction loss.
no code implementations • ICLR 2022 • Yonghyeon LEE, Sangwoong Yoon, MinJun Son, Frank C. Park
The recent success of autoencoders for representation learning can be traced in large part to the addition of a regularization term.
no code implementations • 29 Sep 2021 • Sangwoong Yoon, Jinwon Choi, Yonghyeon LEE, Yung-Kyun Noh, Frank C. Park
As an outlier may deviate from the training distribution in unexpected ways, an ideal OOD detector should be able to detect all types of outliers.
no code implementations • 29 Sep 2021 • Yonghyeon LEE, Seungyeon Kim, Jinwon Choi, Frank C. Park
The only requirement on the part of the user is the choice of a meaningful underlying probability distribution, which is more intuitive and natural to make than what is required in existing ad hoc formulations.