Mitigating Both Covariate and Conditional Shift for Domain Generalization

2022-09-17 · Jianxin Lin, Yongqiang Tang, JunPing Wang, Wensheng Zhang

Domain generalization (DG) aims to learn a model on several source domains, hoping that the model can generalize well to unseen target domains. The distribution shift between domains contains the covariate shift and conditional shift, both of which the model must be able to handle for better generalizability. In this paper, a novel DG method is proposed to deal with the distribution shift via Visual Alignment and Uncertainty-guided belief Ensemble (VAUE). Specifically, for the covariate shift, a visual alignment module is designed to align the distribution of image style to a common empirical Gaussian distribution so that the covariate shift can be eliminated in the visual space. For the conditional shift, we adopt an uncertainty-guided belief ensemble strategy based on the subjective logic and Dempster-Shafer theory. The conditional distribution given a test sample is estimated by the dynamic combination of that of source domains. Comprehensive experiments are conducted to demonstrate the superior performance of the proposed method on four widely used datasets, i.e., Office-Home, VLCS, TerraIncognita, and PACS.

📄 PDF Abstract BibTeX arXiv:2209.08253

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Generalization

Methods 이 논문이 사용한 방법론

Test 설명 없음

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Contrastive Conditional Alignment based on Label Shift Calibration for Imbalanced Domain Adaptation

2024-12-29 · Xiaona Sun, Zhenyu Wu, ZhiQiang Zhan, Yang Ji

Many existing unsupervised domain adaptation (UDA) methods primarily focus on covariate shift, limiting their effectiveness in imbalanced domain adaptation (IDA) where both covariate shift and label shift coexist. Recent…

Domain Adaptation Unsupervised Domain Adaptation

Generalized Domain Adaptation with Covariate and Label Shift CO-ALignment

2019-09-25 · Shuhan Tan, Xingchao Peng, Kate Saenko

Unsupervised knowledge transfer has a great potential to improve the generalizability of deep models to novel domains. Yet the current literature assumes that the label distribution is domain-invariant and only aligns th…

Domain Adaptation Transfer Learning

Learning Fair Invariant Representations under Covariate and Correlation Shifts Simultaneously

2024-08-18 · Dong Li, Chen Zhao, Minglai Shao, Wenjun Wang

Achieving the generalization of an invariant classifier from training domains to shifted test domains while simultaneously considering model fairness is a substantial and complex challenge in machine learning. Existing m…

Domain Generalization Fairness

PIcsC: Partitioning-Induced Covariate Shift Correction

2026-07-28 · Behraj Khan, Behroz Mirza, Syed Ahmad Chan Bukhari, Tahir Qasim Syed arxiv

Covariate shift across training-data partitions biases model selection and parameter estimation in cross-validation, lifelong learning, and federated learning. We propose \textit{Partition-Induced Covariate-shift Correct…

Federated Learning

Flexible Transfer Learning under Support and Model Shift

2014-12-01 · NeurIPS 2014 12 · Xuezhi Wang, Jeff Schneider

Transfer learning algorithms are used when one has sufficient training data for one supervised learning task (the source/training domain) but only very limited training data for a second task (the target/test domain) tha…

Transfer Learning