Test-time adaptation (TTA) methods, which generally rely on the model's
...
This paper presents a simple yet effective approach that improves contin...
Time-series forecasting models often encounter abrupt changes in a given...
Image classification models often learn to predict a class based on
irre...
Image classifiers often rely overly on peripheral attributes that have a...
Despite recent advancements in deep learning, deep networks still suffer...
In image classification, "debiasing" aims to train a classifier to be le...
Despite the unprecedented improvement of face recognition, existing face...
Identifying unexpected objects on roads in semantic segmentation (e.g.,
...
Image classification models tend to make decisions based on peripheral
a...