Unbiased Teacher for Semi-Supervised Object Detection

Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen +4 more
2/18/2021
cs.CVcs.LG

Official code: facebookresearch/unbiased-teacher (435 stars, MIT, last commit 2021-09-10).

Abstract

Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, has made significant progress recently. However, existing works have primarily focused on image classification tasks and neglected object detection which requires more annotation effort. In this work, we revisit the Semi-Supervised Object Detection (SS-OD) and identify the pseudo-labeling bias issue in SS-OD. To address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner. Together with a class-balance loss to downweight overly confident pseudo-labels, Unbiased Teacher consistently improved state-of-the-art methods by significant margins on COCO-standard, COCO-additional, and VOC datasets. Specifically, Unbiased Teacher achieves 6.8 absolute mAP improvements against state-of-the-art method when using 1% of labeled data on MS-COCO, achieves around 10 mAP improvements against the supervised baseline when using only 0.5, 1, 2% of labeled data on MS-COCO.

View on arXivView PDF

Code Implementations(1)

facebookresearch/unbiased-teacherOfficial100%
MIT

PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection

43581PythonFeb 12, 20215 years agoMIT

Similar Papers

Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detection

90% match2025

Co-Training with Active Contrastive Learning and Meta-Pseudo-Labeling on 2D Projections for Deep Semi-Supervised Learning

89% match2025

Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning

89% match1 repo42024

Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classification

88% match2024

Synergy-Guided Regional Supervision of Pseudo Labels for Semi-Supervised Medical Image Segmentation

88% match2024

Collaboration of Teachers for Semi-supervised Object Detection

88% match2024

Cite this paper

@article{liu2021unbiased,
  title  = {Unbiased Teacher for Semi-Supervised Object Detection},
  author = {Yen-Cheng Liu and Chih-Yao Ma and Zijian He and Chia-Wen Kuo and Kan Chen and Peizhao Zhang and Bichen Wu and Zsolt Kira and Peter Vajda},
  year   = {2021},
  eprint = {2102.09480},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2102.09480}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2102.09480.svg)](https://codeofpaper.com/paper/2102.09480)

Discussion