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 …

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 …

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

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

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 …

Large language models (LLMs) are trained on a vast amount of human-written data, but data
providers often remain uncredited. In response to this issue, data valuation (or data …

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 …

Achieving a reliable LiDAR-based object detector in autonomous driving is paramount, but
its success hinges on obtaining large amounts of precise 3D annotations. Active learning …

Data attribution seeks to trace model outputs back to training data. With the recent
development of diffusion models, data attribution has become a desired module to properly …

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 …