Conditional Adversarial Domain Adaptation

By Mingsheng Long, Zhangjie Cao, Jianmin Wang, Michael I. Jordan. 2017

2,865 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Robust Global Representations by Penalizing Local Predictive Power (2019, background): “, 2018) and coercing domain 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”
Transfer without Forgetting (2022, methodology): “Such a simple schema has been recently overcome by more sophisticated domain adaptation algorithms [15,36,35] mainly based on the concept of feature alignment : here, the goal is to reduce the shift between the feature distributions of target and source domains.”
A Comprehensive Survey on Transfer Learning (2019, methodology): “[158] proposed the conditional domain adversarial network (CDAN), which utilizes a conditional domain discriminator to assist adversarial adaptation.”
Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study (2019, methodology): “As stated in [107], DANN cannot capture complex multi-modal structures and it is hard to condition the domain discriminator safely.”
Unsupervised Object Segmentation by Redrawing (2019, methodology): “This technique is also used in adversarial domain adaptation [16, 36, 51] to align embeddings from different domains.”
Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift (2020, background): “such as importance weighting the training data [61, 32, 12], representation learning [22, 3], and adversarial training [19, 67, 44].”
Domain Adaptation by Joint Distribution Invariant Projections (2020, background): “Besides, from the perspective of hypothesis space, we can also explore the deep neural networks to serve as the feature mappings, which, as evidence by [12], [68], have their advantages in handling large-scale visual domain adaptation tasks.”
A Survey of Unsupervised Deep Domain Adaptation (2018, background): “e incorporated. While domain adaptation methods commonly align feature distributions, a different line of research aligns the joint or conditional distribution of the feature and label spaces instead [44, 47, 50, 148, 151, 154, 233, 267]. Researchers found aligning in this manner improves results wh”
Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation (2022, background): “, classification [28, 39], object detection [10, 15], and semantic segmentation [23, 42].”
Federated Adversarial Debiasing for Fair and Transferable Representations (2021, methodology): “CDAN [28] is the first to condition the discriminator prediction on the estimated classes, which aligns with our purpose to maximize the mutual information between user (related to classes) and representation.”
Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives (2022, background): “The solution to UDA is primarily classified into statistic moment matching (e.g., maximum mean discrepancy (MMD) (Long et al., 2018)), domain style transfer (Sankaranarayanan et al., 2018), selftraining (Zou et al., 2019; Liu et al., 2021e,l), and feature-level adversarial learning (Ganin et al.,…”
Under review as a conference paper at ICLR 2020 many domain adaptation methods (2019, methodology): “The 2DAN, JAN: https://github.com/thuml/Xlearn , CDAN+E: https://github.com/thuml/CDAN CoBRF achieves the best performance among all algorithms on Office-31.”
Towards Discriminability and Diversity: Batch Nuclear-Norm Maximization Under Label Insufficient Situations (2020, background): “CDAN [26] 50.”
Environment Inference for Invariant Learning (2020, background): “…2018) leveraged statistical independence regularizers from domain adaptation 13 (Ben-David et al., 2010; Ganin et al., 2016; Tzeng et al., 2017; Long et al., 2018), noting that marginal or conditional independence from domain to prediction relates to the fairness notions of demographic parity…”
Attending to Discriminative Certainty for Domain Adaptation (2019, neutral): “3 CDAN[26] 77.”
Maximum Density Divergence for Domain Adaptation (2020, methodology): “In adversarial domain adaptation [3], [4], [7], there are also a generator and a discriminator.”
An Efficient LSTM Network for Emotion Recognition From Multichannel EEG Signals (2020, background): “[50] proposed Conditional Domain Adversarial Networks (CDANs) for aligning different domains of multimodal distributions in classification problems.”
Out-of-Distribution Generalization via Risk Extrapolation (REx) (2020, background): “Other approaches focus on adversarially learning representations that are invariant with respect to domain-speciﬁc features (Tzeng et al., 2017; Long et al., 2018; Li et al., 2018; Albuquerque et al., 2019).”
The Risks of Invariant Risk Minimization (2020, methodology): “invariance of the covariate distribution p(Φ(x)), but this is typically used for domain adaptation (Ben-David et al., 2010; Ganin & Lempitsky, 2015; Zhang et al., 2015; Long et al., 2018), with assumed access to labeled or unlabeled data from the target distribution.”
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation (2020, background): “homogeneity homogeneous DA dS = dT source and target data are observed in the same space [11, 23, 36, 44–106, 113–151] heterogeneous DA dS 6= dT source and target data are observed in different spaces [107–112]”