Data pruning, which aims to downsize a large training set into a small informative subset, is
crucial for reducing the enormous computational costs of modern deep learning. Though …

Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental
requirement in high-stakes applications. Unfortunately, modern deep neural networks are …

Unlabeled data examples awaiting annotations contain open-set noise inevitably. A few
active learning studies have attempted to deal with this open-set noise for sample selection …

Out-of-distribution~(OOD) detection is fundamental to guaranteeing the reliability of
multimedia applications during deployment in the open world. However, due to the lack of …

We propose a novel framework DropTop that suppresses the shortcut bias in online
continual learning (OCL) while being adaptive to the varying degree of the shortcut bias …

The artificial intelligence research community is continuing to grapple with the ethics of its
work by encouraging researchers to discuss potential positive and negative consequences …

In this dissertation, we propose a systemic framework that prioritizes informative features
and examples to enhance each stage of the development process. Specifically, we prioritize …

In this paper, we present results on improving out-of-domain weather prediction and
uncertainty estimation as part of the\texttt {Shifts Challenge on Robustness and Uncertainty …

Test-Time Adaptation (TTA) aims to quickly adapt a pre-trained Deep Neural Network (DNN)
to shifted test data from unseen distributions. Early TTA works only targeted simple and …

최근 들어 딥러닝 (deep learning) 은 비약적인 발전을이루었으며, 이로 인해 이미지 분류/인식,
영상 인식, 음성 인식, 자연어 번역 등의 성능이 크게 향상되었다. 이러한 딥러닝 발전의 주요 …