{ "id": "2102.09480", "version": "v1", "published": "2021-02-18T17:02:57.000Z", "updated": "2021-02-18T17:02:57.000Z", "title": "Unbiased Teacher for Semi-Supervised Object Detection", "authors": [ "Yen-Cheng Liu", "Chih-Yao Ma", "Zijian He", "Chia-Wen Kuo", "Kan Chen", "Peizhao Zhang", "Bichen Wu", "Zsolt Kira", "Peter Vajda" ], "comment": "Accepted to ICLR 2021; Code is available at https://github.com/facebookresearch/unbiased-teacher", "categories": [ "cs.CV", "cs.LG" ], "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.", "revisions": [ { "version": "v1", "updated": "2021-02-18T17:02:57.000Z" } ], "analyses": { "keywords": [ "semi-supervised object detection", "unbiased teacher", "state-of-the-art method", "image classification tasks", "downweight overly confident pseudo-labels" ], "tags": [ "github project" ], "note": { "typesetting": "TeX", "pages": 0, "language": "en", "license": "arXiv", "status": "editable" } } }