Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9809-9818
Abstract
With the recent development of Semi-Supervised Object Detection (SS-OD) techniques, object detectors can be improved by using a limited amount of labeled data and abundant unlabeled data. However, there are still two challenges that are not addressed: (1) there is no prior SS-OD work on anchor-free detectors, and (2) prior works are ineffective when pseudo-labeling bounding box regression. In this paper, we present Unbiased Teacher v2, which shows the generalization of SS-OD method to anchor-free detectors and also introduces Listen2Student mechanism for the unsupervised regression loss. Specifically, we first present a study examining the effectiveness of existing SS-OD methods on anchor-free detectors and find that they achieve much lower performance improvements under the semi-supervised setting. We also observe that box selection with centerness and the localization-based labeling used in anchor-free detectors cannot work well under the semi-supervised setting. On the other hand, our Listen2Student mechanism explicitly prevents misleading pseudo-labels in the training of bounding box regression; we specifically develop a novel pseudo-labeling selection mechanism based on the Teacher and Student's relative uncertainties. This idea contributes to favorable improvement in the regression branch in the semi-supervised setting. Our method, which works for both anchor-free and anchor-based methods, consistently performs favorably against the state-of-the-art methods in VOC, COCO-standard, and COCO-additional.Keywords
All Related Versions
Funding Information
- DARPA (HR0011-18-S-0044)
- Georgia Tech
This publication has 28 references indexed in Scilit:
- CornerNet: Detecting Objects as Paired Keypoints2018
- Focal Loss for Dense Object Detection2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- SSD: Single Shot MultiBox Detector2016
- A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Training Region-Based Object Detectors with Online Hard Example Mining2016
- Small-World Properties of Facebook Group NetworksComplex Systems, 2014
- Microsoft COCO: Common Objects in Context2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009