paper-with-me

홈 › Papers

Deep Least Squares Alignment for Unsupervised Domain Adaptation

2021-11-03 · Youshan Zhang, Brian D. Davison

Unsupervised domain adaptation leverages rich information from a labeled source domain to model an unlabeled target domain. Existing methods attempt to align the cross-domain distributions. However, the statistical representations of the alignment of the two domains are not well addressed. In this paper, we propose deep least squares alignment (DLSA) to estimate the distribution of the two domains in a latent space by parameterizing a linear model. We further develop marginal and conditional adaptation loss to reduce the domain discrepancy by minimizing the angle between fitting lines and intercept differences and further learning domain invariant features. Extensive experiments demonstrate that the proposed DLSA model is effective in aligning domain distributions and outperforms state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2111.02207

Code (1)

YoushanZhang/Transfer-Learning 공식 구현

Tasks

Domain AdaptationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Unsupervised Domain Adaptation: A Multi-task Learning-based Method

2018-03-25 · Jing Zhang, Wanqing Li, Philip Ogunbona

This paper presents a novel multi-task learning-based method for unsupervised domain adaptation. Specifically, the source and target domain classifiers are jointly learned by considering the geometry of target domain and…

Domain AdaptationMulti-Task LearningUnsupervised Domain Adaptation

Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

2023-05-02 · Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen 외

We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. …

Domain AdaptationUnsupervised Domain Adaptation

Black Box Few-Shot Adaptation for Vision-Language models

2023-04-04 · ICCV 2023 1 · Yassine Ouali, Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos

Vision-Language (V-L) models trained with contrastive learning to align the visual and language modalities have been shown to be strong few-shot learners. Soft prompt learning is the method of choice for few-shot downstr…

Contrastive LearningPrompt LearningRe-Ranking

“Look Ma, no landmarks!” – Unsupervised, Model-based Dense Face Alignment

2020-08-01 · ECCV 2020 8 · Tatsuro Koizumi, William A. P. Smith

no landmarks!"" - Unsupervised, model-based dense face alignment","In this paper, we show how to train an image-to-image network to predict dense correspondence between a face image and a 3D morphable model using only th…

3D Face ReconstructionCamera CalibrationFace Alignment

Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts

2021-06-01 · Bahar Taskesen, Man-Chung Yue, Jose Blanchet, Daniel Kuhn 외

Least squares estimators, when trained on a few target domain samples, may predict poorly. Supervised domain adaptation aims to improve the predictive accuracy by exploiting additional labeled training samples from a sou…

Domain Adaptation