Zero-Shot Domain Adaptation via Kernel Regression on the Grassmannian

Yang, Yongxin; Hospedales, Timothy M.

doi:10.5244/c.29.diffcv.1

Cited by 21 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The term zero-shot domain adaptation has been used by Yang and Hospedales [42,41] and is sometimes called domain generalization. Many zero-shot domain adaptation methods attempt to find domain-invariant representations or models for generalization.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Zero-shot Domain Adaptation without Domain Semantic Descriptors

Kumagai¹,

Iwata²

2018

Preprint

View full text Add to dashboard Cite

We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors. When training and test distributions are different, standard supervised learning methods perform poorly. Zero-shot domain adaptation attempts to alleviate this problem by inferring models that generalize well to unseen domains by using training data in multiple source domains. Existing methods use observed semantic descriptors characterizing domains such as time information to infer the domain-specific models for the unseen domains. However, it cannot always be assumed that such metadata can be used in real-world applications. The proposed method can infer appropriate domain-specific models without any semantic descriptors by introducing the concept of latent domain vectors, which are latent representations for the domains and are used for inferring the models. The latent domain vector for the unseen domain is inferred from the set of the feature vectors in the corresponding domain, which is given in the testing phase. The domain-specific models consist of two components: the first is for extracting a representation of a feature vector to be predicted, and the second is for inferring model parameters given the latent domain vector. The posterior distributions of the latent domain vectors and the domain-specific models are parametrized by neural networks, and are optimized by maximizing the variational lower bound using stochastic gradient descent. The effectiveness of the proposed method was demonstrated through experiments using one regression and two classification tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Zero-shot domain adaptation aims to adapt target domains where there are no data in the training phase by using data in multiple source domains [42,41,27,26,21]. We call these target domains unseen domains.…”

Section: Introductionmentioning

confidence: 99%

Zero-shot Domain Adaptation without Domain Semantic Descriptors

Kumagai¹,

Iwata²

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Two main categories of feature transformation methods are identified [5] among the literature, namely data centric methods and subspace centric methods. The data centric methods seek a unified transformation that projects data from two domains into a domain invariant space to reduce the distributional divergence between domains while preserving data properties in original spaces, such as [6,7,8,9].…”

Section: Introductionmentioning

confidence: 99%

Joint Geometrical and Statistical Alignment for Visual Domain Adaptation

Zhang

Ogunbona

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

515

326

View full text Add to dashboard Cite

This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. We propose a unified framework that reduces the shift between domains both statistically and geometrically, referred to as Joint Geometrical and Statistical Alignment (JGSA). Specifically, we learn two coupled projections that project the source domain and target domain data into lowdimensional subspaces where the geometrical shift and distribution shift are reduced simultaneously. The objective function can be solved efficiently in a closed form. Extensive experiments have verified that the proposed method significantly outperforms several state-of-the-art domain adaptation methods on a synthetic dataset and three different real world cross-domain visual recognition tasks.

show abstract

“…In this work, we consider the most extreme case in which we cannot obtain any target data, called zero-shot domain adaptation. A few recent studies [4,5] have tackled this challenging problem, but they require additional data such as multiple source datasets [4] or target data of another task [5] that are not easy to obtain in practice. In this paper, we propose a novel method of zero-shot domain adaptation that would be more suitable for practical cases.…”

Section: Introductionmentioning

confidence: 99%

Zero-shot Domain Adaptation Based on Attribute Information

Ishii,

Takenouchi,

Sugiyama

2019

Preprint

View full text Add to dashboard Cite

In this paper, we propose a novel domain adaptation method that can be applied without target data. We consider the situation where domain shift is caused by a prior change of a specific factor and assume that we know how the prior changes between source and target domains. We call this factor an attribute, and reformulate the domain adaptation problem to utilize the attribute prior instead of target data. In our method, the source data are reweighted with the sample-wise weight estimated by the attribute prior and the data themselves so that they are useful in the target domain. We theoretically reveal that our method provides more precise estimation of sample-wise transferability than a straightforward attribute-based reweighting approach. Experimental results with both toy datasets and benchmark datasets show that our method can perform well, though it does not use any target data.

show abstract

Zero-Shot Domain Adaptation via Kernel Regression on the Grassmannian

Cited by 21 publications

References 21 publications

Zero-shot Domain Adaptation without Domain Semantic Descriptors

Zero-shot Domain Adaptation without Domain Semantic Descriptors

Joint Geometrical and Statistical Alignment for Visual Domain Adaptation

Zero-shot Domain Adaptation Based on Attribute Information

Contact Info

Product

Resources

About