paper-with-me

Papers

Learning to Learn Single Domain Generalization

2020-03-30 · CVPR 2020 6 · Fengchun Qiao, Long Zhao, Xi Peng

We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training. We propose a new method named adversarial domain augmentation to solve this Out-of-Distribution (OOD) generalization problem. The key idea is to leverage adversarial training to create "fictitious" yet "challenging" populations, from which a model can learn to generalize with theoretical guarantees. To facilitate fast and desirable domain augmentation, we cast the model training in a meta-learning scheme and use a Wasserstein Auto-Encoder (WAE) to relax the widely used worst-case constraint. Detailed theoretical analysis is provided to testify our formulation, while extensive experiments on multiple benchmark datasets indicate its superior performance in tackling single domain generalization.

📄 PDF Abstract BibTeX arXiv:2003.13216

Code (1)

joffery/M-ADA 공식 구현 pytorch

Tasks

Domain GeneralizationMeta-Learning

Similar Papers 제목 키워드 기반

Progressive Domain Expansion Network for Single Domain Generalization

2021-03-30 · CVPR 2021 1 · Lei LI, Ke Gao, Juan Cao, Ziyao Huang 외

Single domain generalization is a challenging case of model generalization, where the models are trained on a single domain and tested on other unseen domains. A promising solution is to learn cross-domain invariant repr…

Contrastive LearningDomain GeneralizationRepresentation Learning

Causality-inspired Latent Feature Augmentation for Single Domain Generalization

2024-06-10 · Jian Xu, Chaojie Ji, Yankai Cao, Ye Li 외

Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains. Under the domain-hungry configuration, how to expand…

Domain Generalization

Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach

2021-08-05 · Xi Peng, Fengchun Qiao, Long Zhao

We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training. We propose Meta-Lea…

Domain GeneralizationImage ClassificationMeta-LearningSemantic Segmentation+3

Domain Generalization using Ensemble Learning

2021-03-18 · Yusuf Mesbah, Youssef Youssry Ibrahim, Adil Mehood Khan

Domain generalization is a sub-field of transfer learning that aims at bridging the gap between two different domains in the absence of any knowledge about the target domain. Our approach tackles the problem of a model's…

Domain GeneralizationEnsemble LearningTransfer Learning

Modality-Agnostic Debiasing for Single Domain Generalization

2023-03-13 · CVPR 2023 1 · Sanqing Qu, Yingwei Pan, Guang Chen, Ting Yao 외

Deep neural networks (DNNs) usually fail to generalize well to outside of distribution (OOD) data, especially in the extreme case of single domain generalization (single-DG) that transfers DNNs from single domain to mult…

Data AugmentationDomain GeneralizationSemantic Segmentation