paper-with-me

홈 › Papers

Understanding and Estimating the Adaptability of Domain-Invariant Representations

2020-01-01 · ICML 2020 1 · Ching-Yao Chuang, Antonio Torralba, Stefanie Jegelka

Learning domain-invariant representations is a popular approach to unsupervised domain adaptation, i.e., generalizing from a source domain with labels to an unlabeled target domain. In this work, we aim to better understand and estimate the effect of domain-invariant representations on generalization to the target. In particular, we study the effect of the complexity of the latent, domain-invariant representation, and find that it has a significant influence on the target risk. Based on these findings, we propose a general approach for addressing this complexity tradeoff in neural networks. We also propose a method for estimating how well a model based on domain-invariant representations will perform on the target domain, without having seen any target labels. Applications of our results include model selection, deciding early stopping, and predicting the adaptability of a model between domains.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationModel SelectionUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Domain-Invariant Representations: A Look on Compression and Weights

2019-09-25 · Victor Bouvier, Céline Hudelot, Clément Chastagnol, Philippe Very 외

Learning Invariant Representations to adapt deep classifiers of a source domain to a new target domain has recently attracted much attention. In this paper, we show that the search for invariance favors the compression …

Domain Adaptation

Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation

2021-08-14 · Yuan Wu, Diana Inkpen, Ahmed El-Roby

Adversarial domain adaptation has made impressive advances in transferring knowledge from the source domain to the target domain by aligning feature distributions of both domains. These methods focus on minimizing domain…

Domain Adaptation

Transfer Learning with Label Noise

2017-07-31 · Xiyu Yu, Tongliang Liu, Mingming Gong, Kun Zhang 외

Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and target domains, recent methods have focus…

DenoisingTransfer Learning

Estimating Generalization under Distribution Shifts via Domain-Invariant Representations

2020-07-06 · Ching-Yao Chuang, Antonio Torralba, Stefanie Jegelka

When machine learning models are deployed on a test distribution different from the training distribution, they can perform poorly, but overestimate their performance. In this work, we aim to better estimate a model's pe…

Domain AdaptationModel Selection

TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification

2025-05-10 · CVPR 2025 1 · Dongyoon Yang, Jihu Lee, Yongdai Kim

Robust domain adaptation against adversarial attacks is a critical research area that aims to develop models capable of maintaining consistent performance across diverse and challenging domains. In this paper, we derive …

Domain AdaptationDomain Generalization