Search Results for author: Duhun Hwang

Found 5 papers, 2 papers with code

Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairing

no code implementations11 Jan 2024 Jaeill Kim, Duhun Hwang, Eunjung Lee, Jangwon Suh, Jimyeong Kim, Wonjong Rhee

In the past few years, contrastive learning has played a central role for the success of visual unsupervised representation learning.

Contrastive Learning Representation Learning

VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution

1 code implementation CVPR 2023 Jaeill Kim, Suhyun Kang, Duhun Hwang, Jungwook Shin, Wonjong Rhee

Since the introduction of deep learning, a wide scope of representation properties, such as decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have been studied to improve the quality of representation.

Disentanglement Domain Generalization +7

Meta-Learning with a Geometry-Adaptive Preconditioner

1 code implementation CVPR 2023 Suhyun Kang, Duhun Hwang, Moonjung Eo, Taesup Kim, Wonjong Rhee

In this study, we propose Geometry-Adaptive Preconditioned gradient descent (GAP) that can overcome the limitations in MAML; GAP can efficiently meta-learn a preconditioner that is dependent on task-specific parameters, and its preconditioner can be shown to be a Riemannian metric.

Few-Shot Image Classification Few-Shot Learning

Statistical Characteristics of Deep Representations: An Empirical Investigation

no code implementations8 Nov 2018 Daeyoung Choi, Kyungeun Lee, Duhun Hwang, Wonjong Rhee

In this study, the effects of eight representation regularization methods are investigated, including two newly developed rank regularizers (RR).

Cannot find the paper you are looking for? You can Submit a new open access paper.