46 citations · 57 across the 10 of their papers we have counts for
10 papers
Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization
Jungsoo Lee, Debasmit Das, Jaegul Choo +1
Test-time adaptation (TTA) methods, which generally rely on the model's predictions (e.g., entropy minimization) to adapt the source pretrained model to the unlabeled target domain…
Improving Scene Text Recognition for Character-Level Long-Tailed Distribution
Sunghyun Park, Sunghyo Chung, Jungsoo Lee +1
Despite the recent remarkable improvements in scene text recognition (STR), the majority of the studies focused mainly on the English language, which only includes few number of ch…
Deep Imbalanced Time-series Forecasting via Local Discrepancy Density
Junwoo Park, Jungsoo Lee, Youngin Cho +4
Time-series forecasting models often encounter abrupt changes in a given period of time which generally occur due to unexpected or unknown events. Despite their scarce occurrences…
DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation
Bum Chul Kwon, Jungsoo Lee, Chaeyeon Chung +3
Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted corr…
Improving Evaluation of Debiasing in Image Classification
Jungsoo Lee, Juyoung Lee, Sanghun Jung +1
Image classifiers often rely overly on peripheral attributes that have a strong correlation with the target class (i.e., dataset bias) when making predictions. Due to the dataset b…
CAFA: Class-Aware Feature Alignment for Test-Time Adaptation
Sanghun Jung, Jungsoo Lee, Nanhee Kim +3
Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-ti…
Revisiting the Importance of Amplifying Bias for Debiasing
Jungsoo Lee, Jeonghoon Park, Daeyoung Kim +3
In image classification, "debiasing" aims to train a classifier to be less susceptible to dataset bias, the strong correlation between peripheral attributes of data samples and a t…
Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children
Jungsoo Lee, Jooyeol Yun, Sunghyun Park +2
Despite the unprecedented improvement of face recognition, existing face recognition models still show considerably low performances in determining whether a pair of child and adul…
Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
Sanghun Jung, Jungsoo Lee, Daehoon Gwak +2
Identifying unexpected objects on roads in semantic segmentation (e.g., identifying dogs on roads) is crucial in safety-critical applications. Existing approaches use images of une…
Learning Debiased Representation via Disentangled Feature Augmentation
Jungsoo Lee, Eungyeup Kim, Juyoung Lee +2
Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These bias…