activity
20102023
most citedViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

540 citations · 900 across the 36 of their papers we have counts for

collaborators

36 papers

math.AP2023

A regularity theory for an initial value problem with a time-measurable pseudo-differential operator in a weighted -space

Jae-Hwan Choi, Ildoo Kim, Jin Bong Lee

In this study, we investigate the existence, uniqueness, and maximal regularity estimates of solutions to homogeneous initial value problems involving time-measurable pseudo-differ…

math.AP2023

A weighted -theory for fully degenerate second-order evolution equations with unbounded time-measurable coefficients

Ildoo Kim

We study the fully degenerate second-order evolution equation given with the zero initial data. He…

math.AP2022★ 2 cited

A weighted -regularity theory for parabolic partial differential equations with time measurable pseudo-differential operators

Jae-Hwan Choi, Ildoo Kim

We obtain the existence, uniqueness, and regularity estimates of the following Cauchy problem \begin{equation}\label{ab eqn} \begin{cases} \partial_t u(t,x)=ψ(t,-i\nabla)u(t,x)+f(t…

cs.LG2022

Contrastive Regularization for Semi-Supervised Learning

Doyup Lee, Sungwoong Kim, Ildoo Kim +3

Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high pe…

cs.CV2021★ 10 cited

Spatially Consistent Representation Learning

Byungseok Roh, Wuhyun Shin, Ildoo Kim +1

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive p…

stat.ML2021★ 540 cited

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

Wonjae Kim, Bokyung Son, Ildoo Kim

Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extra…