activity
20202026
most citedDisentangling Label Distribution for Long-tailed Visual Recognition

23 citations · 34 across the 37 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2023

Unsupervised Speech Representation Pooling Using Vector Quantization

Jeongkyun Park, Kwanghee Choi, Hyunjun Heo +1

With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto appro…

cs.LG2022

TiDAL: Learning Training Dynamics for Active Learning

Seong Min Kye, Kwanghee Choi, Hyeongmin Byun +1

Active learning (AL) aims to select the most useful data samples from an unlabeled data pool and annotate them to expand the labeled dataset under a limited budget. Especially, unc…

cs.LG2022★ 1 cited

Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wild

Donghyun Son, Byounggyu Lew, Kwanghee Choi +5

Social media platforms struggle to protect users from harmful content through content moderation. These platforms have recently leveraged machine learning models to cope with the v…

cs.LG2021

Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection

Seong Min Kye, Kwanghee Choi, Joonyoung Yi +1

Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correcti…

cs.LG2021★ 1 cited

Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning

Kwanghee Choi, Minyoung Choe, Hyelee Lee

Neural architecture search (NAS) has fostered various fields of machine learning. Despite its prominent dedications, many have criticized the intrinsic limitations of high computat…

cs.LG2020

Combating the Instability of Mutual Information-based Losses via Regularization

Kwanghee Choi, Siyeong Lee

Notable progress has been made in numerous fields of machine learning based on neural network-driven mutual information (MI) bounds. However, utilizing the conventional MI-based lo…