46 citations · 57 across the 10 of their papers we have counts for
4 papers · 1 filter
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…