Work

Meta Pseudo Labels

Year: 2021

Type: conference-paper

Abstract: We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art [16]. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student’s performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student.1

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr46437.2021.01139

Authors: Hieu Pham, Zihang Dai, Qizhe Xie, Quoc V. Le

Institution: Google (United States)

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: green

OpenAlex ID: W3180562345

FWCI: 50.78

Cites: 103

Cited by: 643

Related to: 10