Different distribution shifts require different algorithmic and operational interventions.
Methodological research must be grounded by the specific shifts they address. Although …

Investigating active learning, we focus on the relation between the number of labeled
examples (budget size), and suitable querying strategies. Our theoretical analysis shows a …

Active learning (AL) is an effective sample selection approach that annotates only a subset
of the training data to address the challenge of data annotation, and deep learning (DL) is …

Deep active learning aims to reduce the annotation cost for the training of deep models,
which is notoriously data-hungry. Until recently, deep active learning methods were …

Given the large-scale data and the high annotation cost, pretraining-finetuning becomes a
popular paradigm in multiple computer vision tasks. Previous research has covered both the …

A desirable data selection algorithm can efficiently choose the most informative samples to
maximize the utility of limited annotation budgets. However, current approaches …

Deep learning has achieved widespread success in medical image analysis, leading to an
increasing demand for large-scale expert-annotated medical image datasets. Yet, the high …

Modern deep learning systems require huge data sets to achieve impressive performance,
but there is little guidance on how much or what kind of data to collect. Over-collecting data …

Federated learning enables multiple decentralized clients to learn collaboratively without
sharing local data. However, the expensive annotation cost on local clients remains an …

Given a small training data set and a learning algorithm, how much more data is necessary
to reach a target validation or test performance? This question is of critical importance in …