Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration

Tan, Shuhan; Jiao, Jiening; Zheng, Wei‐Shi

doi:10.1109/cvpr.2019.00554

Cited by 20 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Universal domain adaptation (UniDA) [43] is an integration of OSDA and PDA. Weakly supervised OSDA has also been studied [37]. Multi-source open set domain adaptation (MS-OSDA) is a combination of MSDA and OSDA [28].…”

Section: Related Workmentioning

confidence: 99%

Generalized Domain Adaptation

Mitsuzumi¹,

Irie²,

Ikami³

et al. 2021

Preprint

View full text Add to dashboard Cite

Many variants of unsupervised domain adaptation (UDA) problems have been proposed and solved individually. Its side effect is that a method that works for one variant is often ineffective for or not even applicable to another, which has prevented practical applications. In this paper, we give a general representation of UDA problems, named Generalized Domain Adaptation (GDA). GDA covers the major variants as special cases, which allows us to organize them in a comprehensive framework. Moreover, this generalization leads to a new challenging setting where existing methods fail, such as when domain labels are unknown, and class labels are only partially given to each domain. We propose a novel approach to the new setting. The key to our approach is self-supervised class-destructive learning, which enables the learning of class-invariant representations and domain-adversarial classifiers without using any domain labels. Extensive experiments using three benchmark datasets demonstrate that our method outperforms the state-of-the-art UDA methods in the new setting and that it is competitive in existing UDA variations as well.

show abstract

Section: Related Workmentioning

confidence: 99%

Generalized Domain Adaptation

Mitsuzumi¹,

Irie²,

Ikami³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Open-Set Domain Adaptation. Compared to classic closed set domain adaptation [40,8,17,6,37,46,36], open-set domain adaptation manages a more realist task when the target domain contains data from classes never present in the source domain [4,30,25,27,19,13,35,3,32]. Busto et al attempts to study the realistic scenario when the source and target domain both includes exclusive classes from each other [28].…”

Section: Related Workmentioning

confidence: 99%

Towards Novel Target Discovery Through Open-Set Domain Adaptation

Jing

Liu

Ding

2021

Preprint

View full text Add to dashboard Cite

Open-set domain adaptation (OSDA) considers that the target domain contains samples from novel categories unobserved in external source domain. Unfortunately, existing OSDA methods always ignore the demand for the information of unseen categories and simply recognize them as "unknown" set without further explanation. This motivates us to understand the unknown categories more specifically by exploring the underlying structures and recovering their interpretable semantic attributes. In this paper, we propose a novel framework to accurately identify the seen categories in target domain, and effectively recover the semantic attributes for unseen categories. Specifically, structure preserving partial alignment is developed to recognize the seen categories through domain-invariant feature learning. Attribute propagation over visual graph is designed to smoothly transit attributes from seen to unseen categories via visual-semantic mapping. Moreover, two new cross-main benchmarks are constructed to evaluate the proposed framework in the novel and practical challenge. Experimental results on open-set recognition and semantic recovery demonstrate the superiority of the proposed method over other compared baselines.

show abstract

“…The adaptable model is aimed to be learned using the distribution to the multiple domains of the mixed set. Recently, several works [21,22,23] address the open set domain adaptation. They assume that there exist unknown and partially overlapped known classes between domains.…”

Section: Evaluation Protocols In Domain Adaptationmentioning

confidence: 99%

Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation

Ryu¹,

Bae²,

Lim³

2020

Preprint

View full text Add to dashboard Cite

In this paper, we introduce a collaborative training algorithm of balanced random forests for domain adaptation tasks which can avoid the overfitting problem. In real scenarios, most domain adaptation algorithms face the challenges from noisy, insufficient training data. Moreover in open set categorization, unknown or misaligned source and target categories adds difficulty. In such cases, conventional methods suffer from overfitting and fail to successfully transfer the knowledge of the source to the target domain. To address these issues, the following two techniques are proposed. First, we introduce the optimized decision tree construction method, in which the data at each node are split into equal sizes while maximizing the information gain. Compared to the conventional random forests, it generates larger and more balanced decision trees due to the even-split constraint, which contributes to enhanced discrimination power and reduced overfitting. Second, to tackle the domain misalignment problem, we propose the domain alignment loss which penalizes uneven splits of the source and target domain data. By collaboratively optimizing the information gain of the labeled source data as well as the entropy of unlabeled target data distributions, the proposed CoBRF algorithm achieves significantly better performance than the state-of-the-art methods. The proposed algorithm is extensively evaluated in various experimental setups in challenging domain adaptation tasks with noisy and small training data as well as open set domain adaptation problems, for two backbone networks of AlexNet and ResNet-50.

show abstract

Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration

Cited by 20 publications

References 38 publications

Generalized Domain Adaptation

Generalized Domain Adaptation

Towards Novel Target Discovery Through Open-Set Domain Adaptation

Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation

Contact Info

Product

Resources

About