paper-with-me

Papers

Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation

2020-12-04 · Zhiyong Huang, Kekai Sheng, WeiMing Dong, Xing Mei, Chongyang Ma, Feiyue Huang, Dengwen Zhou, Changsheng Xu

Semi-supervised domain adaptation (SSDA) methods have demonstrated great potential in large-scale image classification tasks when massive labeled data are available in the source domain but very few labeled samples are provided in the target domain. Existing solutions usually focus on feature alignment between the two domains while paying little attention to the discrimination capability of learned representations in the target domain. In this paper, we present a novel and effective method, namely Effective Label Propagation (ELP), to tackle this problem by using effective inter-domain and intra-domain semantic information propagation. For inter-domain propagation, we propose a new cycle discrepancy loss to encourage consistency of semantic information between the two domains. For intra-domain propagation, we propose an effective self-training strategy to mitigate the noises in pseudo-labeled target domain data and improve the feature discriminability in the target domain. As a general method, our ELP can be easily applied to various domain adaptation approaches and can facilitate their feature discrimination in the target domain. Experiments on Office-Home and DomainNet benchmarks show ELP consistently improves the classification accuracy of mainstream SSDA methods by 2%~3%. Additionally, ELP also improves the performance of UDA methods as well (81.5% vs 86.1%), based on UDA experiments on the VisDA-2017 benchmark. Our source code and pre-trained models will be released soon.

📄 PDF Abstract BibTeX arXiv:2012.02621

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptationimage-classificationImage ClassificationSemi-supervised Domain Adaptation

Similar Papers 제목 키워드 기반

Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning

2023-02-17 · Lei Tian, Yongqiang Tang, Liangchen Hu, Wensheng Zhang

Domain adaptation manages to transfer the knowledge of well-labeled source data to unlabeled target data. Many recent efforts focus on improving the prediction accuracy of target pseudo-labels to reduce conditional distr…

Domain AdaptationSelf-LearningSemi-supervised Domain AdaptationTransfer Learning

Semi-supervised learning combining backpropagation and STDP: STDP enhances learning by backpropagation with a small amount of labeled data in a spiking neural network

2021-02-21 · Kotaro Furuya, Jun Ohkubo

A semi-supervised learning method for spiking neural networks is proposed. The proposed method consists of supervised learning by backpropagation and subsequent unsupervised learning by spike-timing-dependent plasticity …

Graph-based Label Propagation for Semi-Supervised Speaker Identification

2021-06-15 · Long Chen, Venkatesh Ravichandran, Andreas Stolcke

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve sp…

Speaker IdentificationSpeaker Recognition

Semisupervised Learning on Heterogeneous Graphs and its Applications to Facebook News Feed

2018-05-18 · Cheng Ju, James Li, Bram Wasti, Shengbo Guo

Graph-based semi-supervised learning is a fundamental machine learning problem, and has been well studied. Most studies focus on homogeneous networks (e.g. citation network, friend network). In the present paper, we prop…

Classificationdomain classificationGeneral Classificationregression

Two-View Label Propagation to Semi-supervised Reader Emotion Classification

2016-12-01 · COLING 2016 12 · Shoushan Li, Jian Xu, Dong Zhang, Guodong Zhou

In the literature, various supervised learning approaches have been adopted to address the task of reader emotion classification. However, the classification performance greatly suffers when the size of the labeled data …

ClassificationEmotion ClassificationGeneral ClassificationVocal Bursts Valence Prediction