paper-with-me

Papers

Mapping conditional distributions for domain adaptation under generalized target shift

2021-10-26 · ICLR 2022 4 · Matthieu Kirchmeyer, Alain Rakotomamonjy, Emmanuel de Bezenac, Patrick Gallinari

We consider the problem of unsupervised domain adaptation (UDA) between a source and a target domain under conditional and label shift a.k.a Generalized Target Shift (GeTarS). Unlike simpler UDA settings, few works have addressed this challenging problem. Recent approaches learn domain-invariant representations, yet they have practical limitations and rely on strong assumptions that may not hold in practice. In this paper, we explore a novel and general approach to align pretrained representations, which circumvents existing drawbacks. Instead of constraining representation invariance, it learns an optimal transport map, implemented as a NN, which maps source representations onto target ones. Our approach is flexible and scalable, it preserves the problem's structure and it has strong theoretical guarantees under mild assumptions. In particular, our solution is unique, matches conditional distributions across domains, recovers target proportions and explicitly controls the target generalization risk. Through an exhaustive comparison on several datasets, we challenge the state-of-the-art in GeTarS.

📄 PDF Abstract BibTeX arXiv:2110.15057

Code (1)

mkirchmeyer/ostar 공식 구현 pytorch

Tasks

Domain AdaptationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Deep Generative Domain Adaptation with Temporal Relation Knowledge for Cross-User Activity Recognition

2024-03-12 · Xiaozhou Ye, Kevin I-Kai Wang

In human activity recognition (HAR), the assumption that training and testing data are independent and identically distributed (i.i.d.) often fails, particularly in cross-user scenarios where data distributions vary sign…

Activity RecognitionDomain AdaptationHuman Activity RecognitionRelation+1

Unsupervised Domain Adaptation via Regularized Conditional Alignment

2019-05-26 · ICCV 2019 10 · Safa Cicek, Stefano Soatto

We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignme…

Domain AdaptationUnsupervised Domain Adaptation

Domain Adaptation and Image Classification via Deep Conditional Adaptation Network

2020-06-14 · Pengfei Ge, Chuan-Xian Ren, Dao-Qing Dai, Hong Yan

Unsupervised domain adaptation aims to generalize the supervised model trained on a source domain to an unlabeled target domain. Marginal distribution alignment of feature spaces is widely used to reduce the domain discr…

ClassificationDomain AdaptationGeneral Classificationimage-classification+2

Maximizing Conditional Independence for Unsupervised Domain Adaptation

2022-03-07 · Yi-Ming Zhai, You-Wei Luo

Unsupervised domain adaptation studies how to transfer a learner from a labeled source domain to an unlabeled target domain with different distributions. Existing methods mainly focus on matching the marginal distributio…

Domain AdaptationUnsupervised Domain Adaptation

CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift

2023-05-29 · Anh T Nguyen, Lam Tran, Anh Tong, Tuan-Duy H. Nguyen 외

Unsupervised domain adaptation (UDA) refers to a domain adaptation framework in which a learning model is trained based on the labeled samples on the source domain and unlabeled ones in the target domain. The dominant ex…

Domain AdaptationUnsupervised Domain Adaptation