Adversarial self-training improves robustness and generalization for gradual domain adaptation
Abstract Gradual Domain Adaptation (GDA), in which the learner is provided with additional
intermediate domains, has been theoretically and empirically studied in many contexts …
intermediate domains, has been theoretically and empirically studied in many contexts …
Gradual domain adaptation without indexed intermediate domains
The effectiveness of unsupervised domain adaptation degrades when there is a large
discrepancy between the source and target domains. Gradual domain adaption (GDA) is …
discrepancy between the source and target domains. Gradual domain adaption (GDA) is …
Understanding gradual domain adaptation: Improved analysis, optimal path and beyond
The vast majority of existing algorithms for unsupervised domain adaptation (UDA) focus on
adapting from a labeled source domain to an unlabeled target domain directly in a one-off …
adapting from a labeled source domain to an unlabeled target domain directly in a one-off …
Curriculum reinforcement learning using optimal transport via gradual domain adaptation
Abstract Curriculum Reinforcement Learning (CRL) aims to create a sequence of tasks,
starting from easy ones and gradually learning towards difficult tasks. In this work, we focus …
starting from easy ones and gradually learning towards difficult tasks. In this work, we focus …
Generative adversarial networks for facilitating stain-independent supervised and unsupervised segmentation: a study on kidney histology
A major challenge in the field of segmentation in digital pathology is given by the high effort
for manual data annotations in combination with many sources introducing variability in the …
for manual data annotations in combination with many sources introducing variability in the …
Gradual domain adaptation: Theory and algorithms
Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an
unlabeled target domain in a one-off way. Though widely applied, UDA faces a great …
unlabeled target domain in a one-off way. Though widely applied, UDA faces a great …
Gradual domain adaptation via normalizing flows
S Sagawa, H Hino - Neural Computation, 2025 - direct.mit.edu
Standard domain adaptation methods do not work well when a large gap exists between the
source and target domains. Gradual domain adaptation is one of the approaches used to …
source and target domains. Gradual domain adaptation is one of the approaches used to …
Unsupervisedly training GANs for segmenting digital pathology with automatically generated annotations
M Gadermayr, L Gupta, BM Klinkhammer… - arXiv preprint arXiv …, 2018 - arxiv.org
Recently, generative adversarial networks exhibited excellent performances in semi-
supervised image analysis scenarios. In this paper, we go even further by proposing a fully …
supervised image analysis scenarios. In this paper, we go even further by proposing a fully …
Online continual adaptation with active self-training
Abstract Models trained with offline data often suffer from continual distribution shifts and
expensive labeling in changing environments. This calls for a new online learning paradigm …
expensive labeling in changing environments. This calls for a new online learning paradigm …
Algorithms and theory for supervised gradual domain adaptation
The phenomenon of data distribution evolving over time has been observed in a range of
applications, calling the needs of adaptive learning algorithms. We thus study the problem of …
applications, calling the needs of adaptive learning algorithms. We thus study the problem of …