Search Results for author: Sungjun Lim

Found 5 papers, 0 papers with code

Sufficient Invariant Learning for Distribution Shift

no code implementations24 Oct 2022 Taero Kim, Sungjun Lim, Kyungwoo Song

Moreover, we propose a new algorithm, Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO), to learn sufficient invariant features across domains or groups.

Data Augmentation

Finding Inverse Document Frequency Information in BERT

no code implementations24 Feb 2022 Jaekeol Choi, Euna Jung, Sungjun Lim, Wonjong Rhee

The traditional approach, however, is being rapidly replaced by Neural Ranking Models (NRMs) that can exploit semantic features.

Retrieval

OPTIMAL TRANSPORT, CYCLEGAN, AND PENALIZED LS FOR UNSUPERVISED LEARNING IN INVERSE PROBLEMS

no code implementations25 Sep 2019 Byeongsu Sim, Gyutaek Oh, Sungjun Lim, and Jong Chul Ye

Specifically, we reveal that a cycleGAN architecture can be derived as a dual formulation of the optimal transport problem, if the PLS with a deep learning penalty is used as a transport cost between the two probability measures from measurements and unknown images.

Generative Adversarial Network

CycleGAN with a Blur Kernel for Deconvolution Microscopy: Optimal Transport Geometry

no code implementations26 Aug 2019 Sungjun Lim, Hyoungjun Park, Sang-Eun Lee, Sunghoe Chang, Jong Chul Ye

Deconvolution microscopy has been extensively used to improve the resolution of the wide-field fluorescent microscopy, but the performance of classical approaches critically depends on the accuracy of a model and optimization algorithms.

Generative Adversarial Network Image Deconvolution

Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer

no code implementations5 Apr 2019 Sungjun Lim, Sang-Eun Lee, Sunghoe Chang, Jong Chul Ye

In contrast to the recent CNN approaches for similar problem, the explicit PSF modeling layers improve the robustness of the algorithm.

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