Semi-Supervised Object Detection Algorithm Based on Localization Confidence Weighting

被引：0

作者：

Feng, Zeheng ^{[1
]}

Wang, Feng ^{[1
]}

机构：

[1] School of Information Engineering, Guangdong University of Technology, Guangzhou

来源：

Computer Engineering and Applications | 2024年 / 60卷 / 06期

关键词：

localization confidence; localization loss function; location noise; object detection; pseudo-labels; semi-supervised learning;

D O I：

10.3778/j.issn.1002-8331.2210-0400

中图分类号：

学科分类号：

摘要：

To address the problem of location noise data in the process of screening pseudo-labels, a semi-supervised object detection algorithm based on localization confidence weighting named Soft Teacher-LAH is proposed. Firstly, it introduces a localization-aware output structure LAH by discretizing the network output of localization branch in object detection model. Secondly, a certain confidence index is defined to measure the localization accuracy based on the prediction output of LAH, and an unsupervised localization loss function based on the confidence weighting is designed, which can reduce the negative effect of location noise of pseudo-labels on model training. Experimental results show the performance advantage of the proposed algorithm, for MS COCO datasets, the average accuracy of the proposed algorithm is improved by 1.1, 1.2 and 1.5 percentage points compared with the existing Soft Teacher scheme when the proportion of labeled data in the training set is 1%, 5% and 10% respectively. For PASCAL VOC dataset, the average accuracy of the proposed algorithm is improved by 1.6 percentage points compared with Soft Teacher scheme, when VOC07 and VOC12 are used as labeled and unlabeled training data respectively. © 2024 Editorial Department of Scientia Agricultura Sinica. All rights reserved.

引用

页码：249 / 258

页数：9

共 31 条

[1]

TAN M, LE Q., Efficientnet: rethinking model scaling for convolutional neural networks, International Conference on Machine Learning, pp. 6105-6114, (2019)

[2]

LIU Z, LIN Y, CAO Y, Et al., Swin transformer: hierarchical vision transformer using shifted windows, Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012-10022, (2021)

[3]

REN S, HE K, GIRSHICK R, Et al., Faster RCNN: towards real-time object detection with region proposal networks, Advances in Neural Information Processing Systems, (2015)

[4]

REDMON J, DIVVALA S, GIRSHICK R, Et al., You only look once: unified, real-time object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, (2016)

[5]

CARION N, MASSA F, SYNNAEVE G, Et al., End- to- end object detection with transformers, European Conference on Computer Vision, pp. 213-229, (2020)

[6]

XU M, ZHANG Z, HU H, Et al., End-to-end semi-supervised object detection with soft teacher, Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3060-3069, (2021)

[7]

WEI Z Q, BI H X, LIU X., A graph- based semi- supervised polSAR image classification method using deep convolutional neural networks, Acta Electronica Sinica, 48, 1, pp. 66-74, (2020)

[8]

LI X X, LING Z G, ZOU W., Semi-supervised learning via convolutional neural network for hyperspectral image classification, Journal of Electronic Measurement and Instrumentation, 32, 10, pp. 95-102, (2018)

[9]

SAJJADI M, JAVANMARDI M, TASDIZEN T., Regularization with stochastic transformations and perturbations for deep semi-supervised learning, Advances in Neural Information Processing Systems, (2016)

[10]

LEE D H., Pseudo-label: the simple and efficient semi-supervised learning method for deep neural network, Workshop on Challenges in Representation Learning, (2013)

← 1 2 3 4 →