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, Peter Vajda

Keywords: Object Detection

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.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose Unbiased Teacher to jointly address the pseudo-labeling bias issue and the overfitting issue in semi-supervised object detection, and our model performs favorably against existing works on COCO-standard, COCO-additional, and VOC.

Code: [ facebookresearch/unbiased-teacher](https://github.com/facebookresearch/unbiased-teacher) + [ 3 community implementations](https://paperswithcode.com/paper/?openreview=MJIve1zgR_)

Data: [COCO 10% labeled data](https://paperswithcode.com/dataset/coco-10-labeled-data), [MS COCO](https://paperswithcode.com/dataset/coco)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2102.09480/code)