Deep Domain Generalization via Conditional Invariant Adversarial Networks

By Ya Li, Xinmei Tian, Mingming Gong, Yajing Liu, Tongliang Liu, Kun Zhang, Dacheng Tao. 2018

831 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering

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

In Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

Toward Causal Representation Learning (2021, background): “It also led to a range of follow-up work [32], [78], [97], [114], [115], [152], [153], [156], [167], [195], [204], [243], [263], [267], [277], [278], [281], complementing the studies of Bareinboim and Pearl [14], [185], and it inspired a thread of work in the statistics community exploiting…”
On the Transfer of Disentangled Representations in Realistic Settings (2020, methodology): “In particular, using the architecture from Locatello et al. (2019b), none of the models we trained correctly captured all factors of variation or yielded high-quality reconstructions.”
Causality for Machine Learning (2019, neutral): “…Blöbaum et al., 2016; Guo et al., 2018; Wang et al., 2019; Subbaswamy et al., 2018; Rabanser et al., 2018; Li et al., 2018a; Lipton et al., 2018; Li et al., 2018b; Magliacane et al., 2018; Rojas-Carulla et al., 2018), and nicely complementary to studies of Elias Bareinboim and Judea (Bareinboim…”
Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations (2020, methodology): “This result is a restatement of the one in Li et al. (2018).”
In Search of Lost Domain Generalization (2020, background): “– MMD [Li et al., 2018b] matches the MMD [Gretton et al., 2012] of feature distributions.”
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts (2019, background): “Domain generalization studies the setting where a meta distribution generates multiple environment distributions, some of which are available during training (source), while others are used for testing (target) (Li et al., 2018; Shankar et al., 2018; Muandet et al., 2013; Balaji et al., 2018; Ghifar”
Gradient Matching for Domain Generalization (2021, neutral): “In fact, there are a few works in domain generalization that are inspired by the meta-learning principles, such as Li et al. (2018a); Balaji et al. (2018); Li et al. (2019); Dou et al. (2019).”
Domain Generalization using Causal Matching (2020, methodology): “The results for DANN (Ganin et al., 2016), CDANN (Li et al., 2018d), MMD, C-MMD (Li et al., 2018b), CORAL, C-CORAL (Sun & Saenko, 2016) were computed by using their implementations in DomainBed (Gulrajani & Lopez-Paz, 2020).”
Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (2021, background): “Many extension have been proposed [33, 1, 21], but they are all the same in that they enhance domain invariance.”
RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening (2021, background): “Various approaches such as meta-learning [27, 2, 28, 33], adversarial training [29, 32, 46], autoencoder [15, 29], metric learning [10, 39], data augmentation [64, 16, 67] have been proposed to learn domain-agnostic feature representations.”
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations (2022, methodology): “Related methods have been developed in several areas of machine learning, such as ML Fairness [22, 30, 47, 77, 2, 46], domain adaptation [23, 24] and domain generalization [9, 65, 57, 29, 84] including works on Invariant Risk Minimization and causality [75, 4, 53, 5].”
Domain Generalization: A Survey (2021, methodology): “fore, some domain alignment methods [32], [166], [168] proposed to instead align the class-conditional P ðXjY Þ, assuming that P ðY Þ does not change (see Eq.”
Reducing Domain Gap via Style-Agnostic Networks (2019, background): “A popular approach is learning a shared feature space across multiple source domains, for example, by minimizing Maximum Mean Discrepancy (MMD) [39,16] or adversarial feature alignment [32,33].”
Hand-Object Contact Consistency Reasoning for Human Grasps Generation (2021, methodology): “Improving the generalization ability of neural networks is one of the most important problem in machine learning [8, 30, 11, 28, 33] A initial grasp is predicted by the GraspCVAE decoder , and it is inputted together with the object into ContactNet for predicting a target contact map.”
Domain Generalization via Model-Agnostic Learning of Semantic Features (2019, background): “, by minimizing divergence between marginal distributions of data sources [35], or joint consideration of the class conditional distributions [30].”