activity
20112022
most citedHiTRACE: High-throughput robust analysis for capillary electrophoresis

105 citations · 366 across the 30 of their papers we have counts for

collaborators

52 papers

cs.LG2022

FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks

Jaehee Jang, Heonseok Ha, Dahuin Jung +1

Personalized federated learning is aimed at allowing numerous clients to train personalized models while participating in collaborative training in a communication-efficient manner…

cs.LG20221 cited

Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?

Jisoo Mok, Byunggook Na, Ji-Hoon Kim +2

In Neural Architecture Search (NAS), reducing the cost of architecture evaluation remains one of the most crucial challenges. Among a plethora of efforts to bypass training of each…

cs.LG20211 cited

Scalable Smartphone Cluster for Deep Learning

Byunggook Na, Jaehee Jang, Seongsik Park +7

Various deep learning applications on smartphones have been rapidly rising, but training deep neural networks (DNNs) has too large computational burden to be executed on a single s…

cs.CV202122 cited

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

Jungbeom Lee, Jooyoung Choi, Jisoo Mok +1

Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminati…

cs.CV20218 cited

FICGAN: Facial Identity Controllable GAN for De-identification

Yonghyun Jeong, Jooyoung Choi, Sungwon Kim +5

In this work, we present Facial Identity Controllable GAN (FICGAN) for not only generating high-quality de-identified face images with ensured privacy protection, but also detailed…

cs.CV20212 cited

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models

Jooyoung Choi, Sungwon Kim, Yonghyun Jeong +2

Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in…