Adversarial Multiple Source Domain Adaptation

By Han Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura, João Paulo Costeira, Geoffrey J. Gordon. 2018

619 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Robust Global Representations by Penalizing Local Predictive Power (2019, background): “…invariance via adversarial learning (or further extensions) (Ganin et al., 2016; Bousmalis et al., 2017; Tzeng et al., 2017; Xie et al., 2018; Hoffman et al., 2018; Long et al., 2018; Zhao et al., 2018b; Kumar et al., 2018; Li et al., 2018b; Zhao et al., 2018a; Schoenauer-Sebag et al., 2019).”
Multiple-Source Adaptation with Domain Classifiers (2020, background): “Pei et al. [2018], Zhao et al. [2018] extended single domain adversarial learning techniques to the multiple-source setting to extract domain-invariant features.”
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data (2020, methodology): “Zhao et al. (2018) and Wen et al. (2020) considered MSA with only unlabeled target data available and provided generalization bounds for classification and regression.”
SWAD: Domain Generalization by Seeking Flat Minima (2021, methodology): “where the total number of training data set is In and, for the second inequality, we use the fact that 1 2Div (D, T ) ≤ 1 2I ∑I i=1 Div (Di, T ), which has been proven in [14].”
Moment Matching for Multi-Source Domain Adaptation (2018, background): “Previous theoretical bounds [1, 14, 49] on the target error are based on the H∆H-divergence between the source and target domains.”
A Comprehensive Survey on Transfer Learning (2019, methodology): “[160] utilized domain adversarial networks to solve the multisource transfer learning problem.”
Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision (2020, background): “While many models consider the single-source-single-target adaptation setting, recent works [18, 34] have proposed to address the issue of multiple source domains; it focus on the multiple-sourcesingle-target adaptation setting.”
UDALM: Unsupervised Domain Adaptation through Language Modeling (2021, neutral): “Zhao et al. (2018) propose multi-source domain adversarial networks.”
Under review as a conference paper at ICLR 2020 many domain adaptation methods (2019, background): “Multiple sources and target domains are mixed into the source or target domains in Zhao et al. (2018); Mancini et al. (2018); Hoffman et al. (2018).”
Federated Adversarial Domain Adaptation (2019, neutral): “Zhao et al. (2018) introduce classification and regression error bounds for multi-source domain adaptation.”
Continuously Indexed Domain Adaptation (2020, background): “Adversarial domain adaptation is particularly popular due to its relatively strong theoretical insights (Goodfellow et al., 2014; Zhao et al., 2018; Zhang et al., 2019; Zhao et al., 2019) and its compatibility with neural networks.”
Learning to Optimize Domain Specific Normalization for Domain Generalization (2019, background): “[31] propose to learn features that are invariant to multiple domain shifts through adversarial training, and Guo et al.”
On Learning Invariant Representations for Domain Adaptation (2019, background): “…For methods that aim to learn invariant representations for domain adaptation, an intermediate representation space Z is found through feature transformation g, based on which a common hypothesis h : Z 7→ Y is shared between both domains (Ganin et al., 2016; Tzeng et al., 2017; Zhao et al., 2018b).”
Adversarial target-invariant representation learning for domain generalization (2019, background): “In order to show that, under the mixture assumption, minimizing pair-wise H-divergences leads to better generalization on an unseen target domain, we present a direct extension to our setting of the generalization bound stated by (Zhao et al., 2018), as a Corollary of their Theorem 2.”