pith. sign in

arxiv: 2102.09480 · v1 · pith:BRVCVHEAnew · submitted 2021-02-18 · 💻 cs.CV · cs.LG

Unbiased Teacher for Semi-Supervised Object Detection

Yen-Cheng Liu , Chih-Yao Ma , Zijian He , Chia-Wen Kuo , Kan Chen , Peizhao Zhang , Bichen Wu , Zsolt Kira
show 1 more author
Peter Vajda
This is my paper
classification 💻 cs.CV cs.LG
keywords teacherunbiaseddatadetectionlabeledobjectsemi-supervisedachieves
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Training a Student Expert via Semi-Supervised Foundation Model Distillation

    cs.CV 2026-04 conditional novelty 7.0

    A semi-supervised framework distills vision foundation models into compact instance segmentation experts that outperform their teachers by up to 11.9 AP on Cityscapes and 8.6 AP on ADE20K while being 11 times smaller.

  2. Simple Supervision Is Hard to Beat: A Bitter Lesson from Sparse Target Labels in Domain-Adaptive Object Detection

    cs.CV 2026-06 unverdicted novelty 6.0

    RTSM improves SFDA-OD by 1.7-18.3 AP50 across methods and detectors, and ten sparse-label feedback plugins give only limited method-dependent gains over it.

  3. Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    MS-DePro achieves state-of-the-art performance on multi-source domain adaptation benchmarks for object detection by using depth-guided region proposals and multi-modal alignment of learnable text embeddings.

  4. FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios

    cs.CV 2026-05 unverdicted novelty 5.0

    FDDet is a semi-supervised object detection framework with BBoxMixUp and CGPC that outperforms standard detectors on the new FDD-48 food defect dataset under data-limited real-world conditions.