Partial disentanglement for domain adaptation
Unsupervised domain adaptation is critical to many real-world applications where label
information is unavailable in the target domain. In general, without further assumptions, the …
information is unavailable in the target domain. In general, without further assumptions, the …
Cross-domain few-shot graph classification with a reinforced task coordinator
Cross-domain graph few-shot learning attempts to address the prevalent data scarcity issue
in graph mining problems. However, the utilization of cross-domain data induces another …
in graph mining problems. However, the utilization of cross-domain data induces another …
BuresNet: Conditional bures metric for transferable representation learning
As a fundamental manner for learning and cognition, transfer learning has attracted
widespread attention in recent years. Typical transfer learning tasks include unsupervised …
widespread attention in recent years. Typical transfer learning tasks include unsupervised …
Generalized universal domain adaptation with generative flow networks
We introduce a new problem in unsupervised domain adaptation, termed as Generalized
Universal Domain Adaptation (GUDA), which aims to achieve precise prediction of all target …
Universal Domain Adaptation (GUDA), which aims to achieve precise prediction of all target …
Mot: Masked optimal transport for partial domain adaptation
As an important methodology to measure distribution discrepancy, optimal transport (OT)
has been successfully applied to learn generalizable visual models under changing …
has been successfully applied to learn generalizable visual models under changing …
Distribution shift alignment in visual domain adaptation
E Hatefi, H Karshenas, P Adibi - Expert Systems with Applications, 2024 - Elsevier
Abstract Domain adaptation provides the possibility of utilizing the knowledge gained from
an auxiliary domain to accomplish the task in another related domain. In this paper, a …
an auxiliary domain to accomplish the task in another related domain. In this paper, a …
Mixture domain adaptation to improve semantic segmentation in real-world surveillance
Various tasks encountered in real-world surveillance can be addressed by determining
posteriors (eg by Bayesian inference or machine learning), based on which critical decisions …
posteriors (eg by Bayesian inference or machine learning), based on which critical decisions …
Partial identifiability for domain adaptation
Unsupervised domain adaptation is critical to many real-world applications where label
information is unavailable in the target domain. In general, without further assumptions, the …
information is unavailable in the target domain. In general, without further assumptions, the …
Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation
To overcome the restriction of identical distribution assumption, invariant representation
learning for unsupervised domain adaptation (UDA) has made significant advances in …
learning for unsupervised domain adaptation (UDA) has made significant advances in …
When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights
As a crucial step toward real-world learning scenarios with changing environments, dataset
shift theory and invariant representation learning algorithm have been extensively studied to …
shift theory and invariant representation learning algorithm have been extensively studied to …