Deep Least Squares Alignment for Unsupervised Domain Adaptation
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.
Code (1)
Tasks
Domain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Unsupervised Domain Adaptation: A Multi-task Learning-based Method
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 AdaptationAddressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
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 AdaptationBlack Box Few-Shot Adaptation for Vision-Language models
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
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 AlignmentSequential Domain Adaptation by Synthesizing Distributionally Robust Experts
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