Meta-causal Learning for Single Domain Generalization
- URL: http://arxiv.org/abs/2304.03709v1
- Date: Fri, 7 Apr 2023 15:46:38 GMT
- Title: Meta-causal Learning for Single Domain Generalization
- Authors: Jin Chen, Zhi Gao, Xinxiao Wu, Jiebo Luo
- Abstract summary: Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains)
Existing methods focus on expanding the distribution of the training domain to cover the target domains, but without estimating the domain shift between the source and target domains.
We propose a new learning paradigm, namely simulate-analyze-reduce, which first simulates the domain shift by building an auxiliary domain as the target domain, then learns to analyze the causes of domain shift, and finally learns to reduce the domain shift for model adaptation.
- Score: 102.53303707563612
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Single domain generalization aims to learn a model from a single training
domain (source domain) and apply it to multiple unseen test domains (target
domains). Existing methods focus on expanding the distribution of the training
domain to cover the target domains, but without estimating the domain shift
between the source and target domains. In this paper, we propose a new learning
paradigm, namely simulate-analyze-reduce, which first simulates the domain
shift by building an auxiliary domain as the target domain, then learns to
analyze the causes of domain shift, and finally learns to reduce the domain
shift for model adaptation. Under this paradigm, we propose a meta-causal
learning method to learn meta-knowledge, that is, how to infer the causes of
domain shift between the auxiliary and source domains during training. We use
the meta-knowledge to analyze the shift between the target and source domains
during testing. Specifically, we perform multiple transformations on source
data to generate the auxiliary domain, perform counterfactual inference to
learn to discover the causal factors of the shift between the auxiliary and
source domains, and incorporate the inferred causality into factor-aware domain
alignments. Extensive experiments on several benchmarks of image classification
show the effectiveness of our method.
Related papers
- Domain Generalization via Causal Adjustment for Cross-Domain Sentiment
Analysis [59.73582306457387]
We focus on the problem of domain generalization for cross-domain sentiment analysis.
We propose a backdoor adjustment-based causal model to disentangle the domain-specific and domain-invariant representations.
A series of experiments show the great performance and robustness of our model.
arXiv Detail & Related papers (2024-02-22T13:26:56Z) - Multi-Source Collaborative Gradient Discrepancy Minimization for
Federated Domain Generalization [27.171533040583117]
Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain.
We propose a Multi-source Collaborative Gradient Discrepancy Minimization (MCGDM) method for federated domain generalization.
arXiv Detail & Related papers (2024-01-05T01:21:37Z) - Revisiting the Domain Shift and Sample Uncertainty in Multi-source
Active Domain Transfer [69.82229895838577]
Active Domain Adaptation (ADA) aims to maximally boost model adaptation in a new target domain by actively selecting a limited number of target data to annotate.
This setting neglects the more practical scenario where training data are collected from multiple sources.
This motivates us to target a new and challenging setting of knowledge transfer that extends ADA from a single source domain to multiple source domains.
arXiv Detail & Related papers (2023-11-21T13:12:21Z) - Aggregation of Disentanglement: Reconsidering Domain Variations in
Domain Generalization [9.577254317971933]
We argue that the domain variantions also contain useful information, ie, classification-aware information, for downstream tasks.
We propose a novel paradigm called Domain Disentanglement Network (DDN) to disentangle the domain expert features from the source domain images.
We also propound a new contrastive learning method to guide the domain expert features to form a more balanced and separable feature space.
arXiv Detail & Related papers (2023-02-05T09:48:57Z) - Adversarial Bi-Regressor Network for Domain Adaptive Regression [52.5168835502987]
It is essential to learn a cross-domain regressor to mitigate the domain shift.
This paper proposes a novel method Adversarial Bi-Regressor Network (ABRNet) to seek more effective cross-domain regression model.
arXiv Detail & Related papers (2022-09-20T18:38:28Z) - Domain Adaptation for Sentiment Analysis Using Increased Intraclass
Separation [31.410122245232373]
Cross-domain sentiment analysis methods have received significant attention.
We introduce a new domain adaptation method which induces large margins between different classes in an embedding space.
This embedding space is trained to be domain-agnostic by matching the data distributions across the domains.
arXiv Detail & Related papers (2021-07-04T11:39:12Z) - Gradual Domain Adaptation via Self-Training of Auxiliary Models [50.63206102072175]
Domain adaptation becomes more challenging with increasing gaps between source and target domains.
We propose self-training of auxiliary models (AuxSelfTrain) that learns models for intermediate domains.
Experiments on benchmark datasets of unsupervised and semi-supervised domain adaptation verify its efficacy.
arXiv Detail & Related papers (2021-06-18T03:15:25Z) - FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation [26.929772844572213]
We introduce a fixed ratio-based mixup to augment multiple intermediate domains between the source and target domain.
We train the source-dominant model and the target-dominant model that have complementary characteristics.
Through our proposed methods, the models gradually transfer domain knowledge from the source to the target domain.
arXiv Detail & Related papers (2020-11-18T11:58:19Z) - Domain Adaptation for Semantic Parsing [68.81787666086554]
We propose a novel semantic for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain.
Our semantic benefits from a two-stage coarse-to-fine framework, thus can provide different and accurate treatments for the two stages.
Experiments on a benchmark dataset show that our method consistently outperforms several popular domain adaptation strategies.
arXiv Detail & Related papers (2020-06-23T14:47:41Z) - Unsupervised Domain Adaptation with Progressive Domain Augmentation [34.887690018011675]
We propose a novel unsupervised domain adaptation method based on progressive domain augmentation.
The proposed method generates virtual intermediate domains via domain, progressively augments the source domain and bridges the source-target domain divergence.
We conduct experiments on multiple domain adaptation tasks and the results shows the proposed method achieves the state-of-the-art performance.
arXiv Detail & Related papers (2020-04-03T18:45:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.