A survey of multi-source domain adaptation

By Shiliang Sun, Honglei Shi, Yuanbin Wu. Information Fusion, 2015

334 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/322e28b752c8a60a8826b895aa053449c120a8f5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Domain Adaptation for Medical Image Analysis: A Survey (2021, positive): “Multi-source domain adaptation [14], [15], [152]–[154], aiming to utilize training data from multi-source domains to improve models’ transferability on the target domain, is of great clinical signiﬁcance.”
A review of natural language processing techniques for opinion mining systems (2017, background): “[104] provided a comprehensive survey on multi-source domain adaptation including representative work in algorithms and theoretical results.”
A Review of Domain Adaptation without Target Labels (2019, background): “are not considered here, but the interested readermay refer to [19], [20], [21].”
A Survey of Unsupervised Deep Domain Adaptation (2018, methodology): “One earlier survey focuses on the multi-source scenario [227], while we focus on the more prevalent singlesource scenario.”
Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives (2022, background): “There are several previous review papers focusing on domain adaptation (Beijbom, 2012; Bungum and Gambäck, 2011; Betlehem et al., 2015; Sun et al., 2015; Wang and Deng, 2018; Csurka, 2017; Zhao et al., 2018; Kouw, 2018; Kouw and Loog, 2019; Zhao et al., 2020b; Wilson and Cook, 2020; Ramponi and Plan”
Opinion Mining and Information Fusion: A survey (2016, background): “[159] exhibit a survey on multi-source domain adaptation, in which they comment on the latest advancements concerning the problem of adapting training data to test data from a different domain.”
Towards Out-Of-Distribution Generalization: A Survey (2021, background): “The detailed illustration of domain adaptation meth-ods is beyond the scope of this paper, curious readers may refer to some well established surveys [23], [24], [25], [26].”
Recent Advances in Open Set Recognition: A Survey (2018, background): “This seems to have the flavor of domain adaptation having multiple source domains and one target domain (mS1T) [172], [173], [174], [175] to some extent.”
Storage Fit Learning with Feature Evolvable Streams (2020, background): “Note that the setting of feature evolvable learning is different from transfer learning (Pan and Yang 2010) or domain adaptation (Jiang 2008; Sun, Shi, and Wu 2015).”
Approximately optimal domain adaptation with Fisher's Linear Discriminant Analysis (2023, methodology): “…2021), and continual learning (Van de Ven & Tolias, 2019; Hadsell et al., 2020; De Lange et al., 2021; Vogelstein et al., 2022) can mitigate this “small data effect” but still require a sufﬁcient amount of context-speciﬁc data to train a model that can then be updated to the context of interest.”