Adversarial target-invariant representation learning for domain generalization
By Isabela Albuquerque, João Monteiro, Tiago H. Falk, Ioannis Mitliagkas. 2019
55 citations recorded by the source corpus.
Subfields: Representation & Self-Supervised Learning, Safety, Robustness & Interpretability
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
- Yoshua Bengio
- Aaron C. Courville
- Pascal Vincent
- Peng Cui
- Jörn-Henrik Jacobsen
- Shruti Tople
- Amit Sharma
- Divyat Mahajan
In Safety, Robustness & Interpretability
- Divyat Mahajan
- Pascal Vincent
- Aaron C. Courville
- Jörn-Henrik Jacobsen
- Amit Sharma
- David Lopez-Paz
- Ishaan Gulrajani
- Simon Lacoste-Julien
Citations in the corpus
- Stochastic Hamiltonian Gradient Methods for Smooth Games (2020, background): “Indeed, in problems like domain generalization (Albuquerque et al., 2019), generative adversarial networks (Goodfellow et al.”
- In Search of Lost Domain Generalization (2020, background): “Albuquerque et al. (2020) introduce the self-supervised task of predicting responses to Gabor filter banks, in order to learn more transferrable features. Wang et al. (2019) remove textural information from images to improve domain generalization. Volpi et al. (2018) show that training with adversar”
- Towards Out-Of-Distribution Generalization: A Survey (2021, background): “There are works [6], [44] [46] propose an additional entropy-regularization approach that learns invariant representations via minimizing the KL-divergence between the conditional distribution of different source domains.”
- 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).”
- Generalizing to Unseen Domains: A Survey on Domain Generalization (2021, methodology): “Domain adversarial learning: DANN [91, 92]/ MMD-AAE [72]/ DLOW [93]/ CIAN [94]/ ER [96]/ MADDG [95]/ FSUS [45]/ MMLD [97]/ DANNCE [98]/ CAADG [99]/ SSDG [100]/ AdaRNN [79] ASR-Norm [81]/ SADG [101]/ [102, 103]”
- Domain Generalization using Causal Matching (2020, methodology): “To avoid overfitting, a popular technique is to learn a common feature representation across all training domains that can be subsequently used to train a classifier [1, 2, 3, 4, 5, 6, 14, 15, 16, 17].”