1 citations · 2 across the 7 of their papers we have counts for
7 papers
Task-Specific Preconditioner for Cross-Domain Few-Shot Learning
Suhyun Kang, Jungwon Park, Wonseok Lee +1
Cross-Domain Few-Shot Learning~(CDFSL) methods typically parameterize models with task-agnostic and task-specific parameters. To adapt task-specific parameters, recent approaches h…
Towards a Better Evaluation of Out-of-Domain Generalization
Duhun Hwang, Suhyun Kang, Moonjung Eo +2
The objective of Domain Generalization (DG) is to devise algorithms and models capable of achieving high performance on previously unseen test distributions. In the pursuit of this…
A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression
Moonjung Eo, Suhyun Kang, Wonjong Rhee
Filter pruning and low-rank decomposition are two of the foundational techniques for structured compression. Although recent efforts have explored hybrid approaches aiming to integ…
Towards a Rigorous Analysis of Mutual Information in Contrastive Learning
Kyungeun Lee, Jaeill Kim, Suhyun Kang +1
Contrastive learning has emerged as a cornerstone in recent achievements of unsupervised representation learning. Its primary paradigm involves an instance discrimination task with…
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution
Jaeill Kim, Suhyun Kang, Duhun Hwang +2
Since the introduction of deep learning, a wide scope of representation properties, such as decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have…
Meta-Learning with a Geometry-Adaptive Preconditioner
Suhyun Kang, Duhun Hwang, Moonjung Eo +2
Model-agnostic meta-learning (MAML) is one of the most successful meta-learning algorithms. It has a bi-level optimization structure where the outer-loop process learns a shared in…
The Geometric Occam's Razor Implicit in Deep Learning
Benoit Dherin, Michael Munn, David G. T. Barrett
In over-parameterized deep neural networks there can be many possible parameter configurations that fit the training data exactly. However, the properties of these interpolating so…