The goal of data attribution is to trace model predictions back to training data. Despite a long
line of work towards this goal, existing approaches to data attribution tend to force users to …

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

Active domain adaptation (ADA) aims to improve the model adaptation performance by
incorporating the active learning (AL) techniques to label a maximally-informative subset of …

Good models require good training data. For overparameterized deep models, the causal
relationship between training data and model predictions is increasingly opaque and poorly …

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 …

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 …

Object detectors trained with weak annotations are affordable alternatives to fully-supervised
counterparts. However, there is still a significant performance gap between them. We …

The existing pose estimation approaches often require a large number of annotated images
to attain good estimation performance, which are laborious to acquire. To reduce the human …