Evolving Domain Generalization
Not on the map. Why?
Abstract (arXiv)
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data. Existing domain generalization methods ignore the relationship between tasks, implicitly assuming that all the tasks are sampled from a stationary environment. Therefore, they can fail when deployed in an evolving environment. To this end, we formulate and study the evolving domain generalization (EDG) scenario, which exploits not only the source data but also their evolving pattern to generate a model for the unseen task. Our theoretical result reveals the benefits of modeling the relation between two consecutive tasks by learning a globally consistent directional mapping function. In practice, our analysis also suggests solving the DDG problem in a meta-learning manner, which leads to directional prototypical network, the first method for the DDG problem. Empirical evaluation of both synthetic and real-world data sets validates the effectiveness of our approach.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 31 May 2022.
Builds on
31 of 53 references.
References · 31
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2019Invariant Risk Minimizationcited by 1,832
- 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
- 2020In Search of Lost Domain Generalizationcited by 1,042
- 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
- 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
- 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
- 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
- 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
- 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
19 more
- 2017Functional Map of the Worldcited by 338
- 2020Learning to Learn Single Domain Generalizationcited by 295
- 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
- 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 262
- 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
- 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 245
- 2020Improve Unsupervised Domain Adaptation with Mixup Trainingcited by 185
- 2017Domain Generalization by Marginal Transfer Learningcited by 180
- 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
- 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
- 2019DIVA: Domain Invariant Variational Autoencoderscited by 114
- 2018Best sources forward: domain generalization through source-specific netscited by 81
- 2020Continuously Indexed Domain Adaptationcited by 74
- 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
- 2015A Century of Portraits: A Visual Historical Record of American High School Yearbookscited by 54
- 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
- 2018Multi-component Image Translation for Deep Domain Generalizationcited by 40
- 2021Aggregating From Multiple Target-Shifted Sourcescited by 24
- 2021On the benefits of representation regularization in invariance based domain generalizationcited by 17
Built on by
Citing papers per year: 2023: 1.
1 paper.