A comprehensive survey on test-time adaptation under distribution shifts
Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …
process that can effectively generalize to test samples, even in the presence of distribution …
[HTML][HTML] A survey on deep learning-based monocular spacecraft pose estimation: Current state, limitations and prospects
Estimating the pose of an uncooperative spacecraft is an important computer vision problem
for enabling the deployment of automatic vision-based systems in orbit, with applications …
for enabling the deployment of automatic vision-based systems in orbit, with applications …
Joint learning of label and environment causal independence for graph out-of-distribution generalization
We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD
algorithms either rely on restricted assumptions or fail to exploit environment information in …
algorithms either rely on restricted assumptions or fail to exploit environment information in …
EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition
In this paper we make the first attempt at achieving the cross-modal (ie image-to-events)
adaptation for event-based object recognition without accessing any labeled source image …
adaptation for event-based object recognition without accessing any labeled source image …
Source-free unsupervised adaptive segmentation for knee joint MRI
Knee osteoarthritis is a prevalent disease worldwide. The automatic segmentation of knee
tissues in magnetic resonance (MR) images has important clinical utility in assessing knee …
tissues in magnetic resonance (MR) images has important clinical utility in assessing knee …
T-TIME: Test-time information maximization ensemble for plug-and-play BCIs
Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) enables
direct communication between the human brain and a computer. Due to individual …
direct communication between the human brain and a computer. Due to individual …
Enhancing and adapting in the clinic: Source-free unsupervised domain adaptation for medical image enhancement
Medical imaging provides many valuable clues involving anatomical structure and
pathological characteristics. However, image degradation is a common issue in clinical …
pathological characteristics. However, image degradation is a common issue in clinical …
Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation
Abstract Open-Set Source-Free Domain Adaptation aims to transfer knowledge in realistic
scenarios where the target domain has additional unknown classes compared to the limited …
scenarios where the target domain has additional unknown classes compared to the limited …
Active test-time adaptation: Theoretical analyses and an algorithm
Test-time adaptation (TTA) addresses distribution shifts for streaming test data in
unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely …
unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely …
A novel generalized source-free domain adaptation approach for cross-domain industrial fault diagnosis
Abstract Domain adaptation has been widely applied in data-driven fault diagnosis tasks to
address the domain shift problem between source and target data. However, conventional …
address the domain shift problem between source and target data. However, conventional …