paper-with-me

홈 › Papers

Co-Training for Domain Adaptation

2011-12-01 · NeurIPS 2011 12 · Minmin Chen, Kilian Q. Weinberger, John Blitzer

Domain adaptation algorithms seek to generalize a model trained in a source domain to a new target domain. In many practical cases, the source and target distributions can differ substantially, and in some cases crucial target features may not have support in the source domain. In this paper we introduce an algorithm that bridges the gap between source and target domains by slowly adding both the target features and instances in which the current algorithm is the most confident. Our algorithm is a variant of co-training, and we name it CODA (Co-training for domain adaptation). Unlike the original co-training work, we do not assume a particular feature split. Instead, for each iteration of co-training, we add target features and formulate a single optimization problem which simultaneously learns a target predictor, a split of the feature space into views, and a shared subset of source and target features to include in the predictor. CODA significantly out-performs the state-of-the-art on the 12-domain benchmark data set of Blitzer et al.. Indeed, over a wide range (65 of 84 comparisons) of target supervision, ranging from no labeled target data to a relatively large number of target labels, CODA achieves the best performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Similar Papers 제목 키워드 기반

Semi-Supervised Adversarial Discriminative Domain Adaptation

2021-09-27 · Thai-Vu Nguyen, Anh Nguyen, Nghia Le, Bac Le

Domain adaptation is a potential method to train a powerful deep neural network, which can handle the absence of labeled data. More precisely, domain adaptation solving the limitation called dataset bias or domain shift …

Domain AdaptationEmotion Recognition

Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation

2021-03-08 · CVPR 2021 1 · Jianzhong He, Xu Jia, Shuaijun Chen, Jianzhuang Liu

Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framew…

Domain AdaptationMulti-Source Unsupervised Domain AdaptationSemantic SegmentationUnsupervised Domain Adaptation

Self-Adaptation for Unsupervised Domain Adaptation

2019-09-01 · RANLP 2019 9 · Xia Cui, Danushka Bollegala

Lack of labelled data in the target domain for training is a common problem in domain adaptation. To overcome this problem, we propose a novel unsupervised domain adaptation method that combines projection and self-train…

Domain AdaptationUnsupervised Domain Adaptation

A Brief Review of Domain Adaptation

2020-10-07 · Abolfazl Farahani, Sahar Voghoei, Khaled Rasheed, Hamid R. Arabnia

Classical machine learning assumes that the training and test sets come from the same distributions. Therefore, a model learned from the labeled training data is expected to perform well on the test data. However, This a…

BIG-bench Machine LearningDomain AdaptationUnsupervised Domain Adaptation

Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey

2021-04-14 · Danielle Saunders

The development of deep learning techniques has allowed Neural Machine Translation (NMT) models to become extremely powerful, given sufficient training data and training time. However, systems struggle when translating t…

Domain AdaptationMachine TranslationNMTTranslation