paper-with-me

홈 › Papers

Learning from a Complementary-label Source Domain: Theory and Algorithms

2020-08-04 · Yiyang Zhang, Feng Liu, Zhen Fang, Bo Yuan, Guangquan Zhang, Jie Lu

In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain. However, collecting fully-true-label data in the source domain is high-cost and sometimes impossible. Compared to the true labels, a complementary label specifies a class that a pattern does not belong to, hence collecting complementary labels would be less laborious than collecting true labels. Thus, in this paper, we propose a novel setting that the source domain is composed of complementary-label data, and a theoretical bound for it is first proved. We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA). To this end, a complementary label adversarial network} (CLARINET) is proposed to solve CC-UDA and PC-UDA problems. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines on handwritten-digits-recognition and objects-recognition tasks.

📄 PDF Abstract BibTeX arXiv:2008.01454

Code (1)

Yiyang98/BFUDA 공식 구현 pytorch

Tasks

Domain AdaptationUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Residual Connection 설명 없음
Dilated Causal Convolution A Dilated Causal Convolution is a causal convolution where the filter is applied over an area larger than its length by…
Attention 설명 없음
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Weight Normalization Weight Normalization is a normalization method for training neural networks. It is inspired by batch normalization,…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation

2020-07-29 · Yiyang Zhang, Feng Liu, Zhen Fang, Bo Yuan 외

In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collec…

Domain AdaptationUnsupervised Domain Adaptation

Self-training Avoids Using Spurious Features Under Domain Shift

2020-06-17 · NeurIPS 2020 12 · Yining Chen, Colin Wei, Ananya Kumar, Tengyu Ma

In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close. In practice, conditional entropy minimization and pseudo-labeling work even when the domain shifts a…

Domain AdaptationUnsupervised Domain Adaptation

A Theory of Multiple-Source Adaptation with Limited Target Labeled Data

2020-07-19 · Yishay Mansour, Mehryar Mohri, Jae Ro, Ananda Theertha Suresh 외

We present a theoretical and algorithmic study of the multiple-source domain adaptation problem in the common scenario where the learner has access only to a limited amount of labeled target data, but where the learner h…

Domain AdaptationModel Selection

Active Learning for Crowd-Sourced Databases

2012-09-17 · Barzan Mozafari, Purnamrita Sarkar, Michael J. Franklin, Michael. I. Jordan 외

Crowd-sourcing has become a popular means of acquiring labeled data for a wide variety of tasks where humans are more accurate than computers, e.g., labeling images, matching objects, or analyzing sentiment. However, rel…

Active LearningBIG-bench Machine Learning

Scaling Unsupervised Domain Adaptation through Optimal Collaborator Selection and Lazy Discriminator Synchronization

2021-01-01 · Akhil Mathur, Shaoduo Gan, Anton Isopoussu, Fahim Kawsar 외

Breakthroughs in unsupervised domain adaptation (uDA) have opened up the possibility of adapting models from a label-rich source domain to unlabeled target domains. Prior uDA works have primarily focused on improving ada…

Domain AdaptationPrivacy PreservingUnsupervised Domain Adaptation