A Semi-Supervised Object Detection Algorithm Based on Teacher-Student Models with Strong-Weak Heads
Open Access
- 22 November 2022
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 11 (23) , 3849
Abstract
Semi-supervised object detection algorithms based on the self-training paradigm produce pseudo bounding boxes with unavoidable noise. We propose a semi-supervised object detection algorithm based on teacher-student models with strong-weak heads to cope with this problem. The strong and weak heads of the teacher model solve the quality measurement problem of pseudo label localization to obtain higher-quality pseudo labels. The strong and weak heads of the student model are decoupled to reduce the negative impact of pseudo label noise on classification and regression. We reach 52.5 mAP (+1.8) on the PASCAL visual object classes (PASCAL VOC) dataset and even up to 53.5 mAP (+3.2) by using Microsoft common objects in context (MS-COCO) train2017 as additional unlabeled data. On the MS-COCO dataset, our method also improves about 1.0 mAP with the experimental configurations of 10% COCO and COCO-full as labeled data.Keywords
Funding Information
- Scientific Research Foundation of Zhejiang University City College (X-202204, X-202106)
This publication has 30 references indexed in Scilit:
- Focal Loss for Dense Object Detection2017
- Mask R-CNN2017
- Feature Pyramid Networks for Object Detection2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer2016
- SSD: Single Shot MultiBox Detector2016
- Deep Residual Learning for Image Recognition2016
- Fast R-CNN2015
- Watch and learn: Semi-supervised learning of object detectors from videos2015
- Experimental comparison among Fast Block Matching Algorithms (FBMAs) for motion estimation and object tracking2011