Deep Domain Generalization via Conditional Invariant Adversarial Networks

@inproceedings{Li2018DeepDG,
  title={Deep Domain Generalization via Conditional Invariant Adversarial Networks},
  author={Ya Feng Li and Xinmei Tian and Mingming Gong and Yajing Liu and Tongliang Liu and Kun Zhang and Dacheng Tao},
  booktitle={ECCV},
  year={2018}
}
Domain generalization aims to learn a classification model from multiple source domains and generalize it to unseen target domains. A critical problem in domain generalization involves learning domain-invariant representations. Let X and Y denote the features and the labels, respectively. Under the assumption that the conditional distribution P(Y|X) remains unchanged across domains, earlier approaches to domain generalization learned the invariant representation T(X) by minimizing the… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 30 CITATIONS

Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization

VIEW 10 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Butterfly: A Panacea for All Difficulties in Wildly Unsupervised Domain Adaptation

VIEW 1 EXCERPT
CITES METHODS

Causality for Machine Learning

VIEW 3 EXCERPTS
CITES BACKGROUND & RESULTS

Compact Feature Learning for Multi-Domain Image Classification

VIEW 2 EXCERPTS
CITES METHODS

Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation

VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Domain Generalization via Invariant Feature Representation

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Fisher discriminant analysis with kernels

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Deep Domain Generalization With Structured Low-Rank Constraint

Algorithm-Dependent Generalization Bounds for Multi-Task Learning.

Deeper, Broader and Artier Domain Generalization

VIEW 3 EXCERPTS