paper-with-me

Papers

Learning to Learn Domain-invariant Parameters for Domain Generalization

2022-11-04 · Feng Hou, Yao Zhang, Yang Liu, Jin Yuan, Cheng Zhong, Yang Zhang, Zhongchao shi, Jianping Fan, Zhiqiang He

Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains. Motivated by the insight that only partial parameters of DNNs are optimized to extract domain-invariant representations, we expect a general model that is capable of well perceiving and emphatically updating such domain-invariant parameters. In this paper, we propose two modules of Domain Decoupling and Combination (DDC) and Domain-invariance-guided Backpropagation (DIGB), which can encourage such general model to focus on the parameters that have a unified optimization direction between pairs of contrastive samples. Our extensive experiments on two benchmarks have demonstrated that our proposed method has achieved state-of-the-art performance with strong generalization capability.

📄 PDF Abstract BibTeX arXiv:2211.04582

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Generalization

Methods 이 논문이 사용한 방법론

fail 설명 없음
Test 설명 없음

Similar Papers 제목 키워드 기반

Bayesian Domain Invariant Learning via Posterior Generalization of Parameter Distributions

2023-10-25 · Shiyu Shen, Bin Pan, Tianyang Shi, Tao Li 외

Domain invariant learning aims to learn models that extract invariant features over various training domains, resulting in better generalization to unseen target domains. Recently, Bayesian Neural Networks have achieved …

Domain GeneralizationVariational Inference

Learning to Learn with Variational Information Bottleneck for Domain Generalization

2020-07-15 · ECCV 2020 8 · Ying-Jun Du, Jun Xu, Huan Xiong, Qiang Qiu 외

Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift. In this paper, we address both problems. We introduce a probabilistic meta-learning …

Domain GeneralizationMeta-LearningPrediction

Learning Transferable Parameters for Unsupervised Domain Adaptation

2021-08-13 · Zhongyi Han, Haoliang Sun, Yilong Yin

Unsupervised domain adaptation (UDA) enables a learning machine to adapt from a labeled source domain to an unlabeled domain under the distribution shift. Thanks to the strong representation ability of deep neural networ…

Domain Adaptationimage-classificationImage ClassificationKeypoint Detection+2

TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification

2021-11-29 · Yichao Yan, Junjie Li, Shengcai Liao, Jie Qin 외

Domain generalizable person re-identification aims to apply a trained model to unseen domains. Prior works either combine the data in all the training domains to capture domain-invariant features, or adopt a mixture of e…

Domain GeneralizationGeneralizable Person Re-identificationMixture-of-ExpertsPerson Re-Identification+1

Deep Domain Generalization via Conditional Invariant Adversarial Networks

2018-09-01 · ECCV 2018 9 · Ya Li, Xinmei Tian, Mingming Gong, Yajing Liu 외

Domain generalization aims to learn a classification model from multiple source domains and generalize it to unseen target domains. A critical problem in domain generalization involves learning domain-invariant represent…

Domain GeneralizationRepresentation Learning