检索结果-内蒙古大学图书馆

4th International Conference on Computer, Internet of Things and Control Engineering

作者： Long, Zuwei Li, Jun Univ Sci & Technol China Dept Automat Hefei Peoples R China Univ Sci & Technol China Inst Adv Technol Hefei Peoples R China

ISBN: (纸本)9798400711848

Recent advancements in semi-supervised object detection have shown promising results. However, the dense information predictions from the teacher model are often discarded. To address this issue, we propose the Pixel-level Contrastive Learning (PCL) module and the Regression Distribution Distillation (RDD) module. The PCL module effectively mines the dense classification information embedded in the teacher model, providing the student model with more precise supervisory signals. On the other hand, the RDD module leverages the dense regression information from the teacher model to explicitly supervise the regression branch of the student model. These modules collectively enhance the model's classification and regression capabilities. Experimental results on the COCO dataset demonstrate that our approach achieves satisfactory performance, validating its effectiveness in semi-supervised object detection tasks.

关键词： semi-supervised object detection object detection Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

semi-supervised object detection IN REMOTE SENSING IMAGES BASED ON ACTIVE LEARNING

SEMI-SUPERVISED OBJECT DETECTION IN REMOTE SENSING IMAGES BA...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Wang, Yuhao Yao, Lifan Meng, Gang Zhang, Xinye Song, Jiayun Zhang, Haopeng Beihang Univ Sch Astronaut Beijing 102206 Peoples R China Beihang Univ Qingdao Res Inst Shandong 266104 Peoples R China Beijing Inst Remote Sensing Informat Beijing 100011 Peoples R China

ISBN: (纸本)9798350320107

The emergence of semi-supervised object detection (SSOD) techniques has led to notable improvements in object detection capabilities by leveraging a restricted quantity of labeled data and a copious amount of unlabeled data. However, there are two challenging issues that need to be addressed in remote sensing images. Firstly, the complex background and large variation in target scales in remote sensing images can result in poor quality of pseudo-labels. Secondly, the long-tailed distribution problem, where some categories have a large number of instances while others have very few, is also common in remote sensing images. In this paper, we address SSOD in remote sensing images characterized by a long-tailed distribution. We propose an active learning strategy for selecting labeled data in the process of semi-supervised learning. The model training is decoupled into the training of backbone and detector. This idea contributes to favorable improvement in the regression branch and our method can achieve significant results on DOTA-v1.0 dataset.

关键词： semi-supervised object detection activate learning long-tailed distribution remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Novel semi-supervised object detection Approach via Scale Rebalancing and Global Proposal Contrast Consistency

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第1期35卷 232-244页

作者： Liu, Bo Yang, Chengrong Guo, Jing Yang, Yun Yunnan Univ Sch Software Kunming 650504 Peoples R China Yunnan Prov Key Lab Software Engn Kunming 650504 Peoples R China

semi-supervised object detection (SSOD) is a method that uses a small amount of labeled data and a large amount of unlabeled data to improve the performance of object detection. However, existing SSOD methods face the challenges of scale imbalance and class inconsistency, resulting in large differences in detection results across different scales and classes. To overcome these challenges, we propose a Scale-Rebalanced Global Proposal Contrast Consistency (SGPC) approach, which has the following three advantages: 1) we design a Scale-Rebalanced Input (SRI) structure, which adjusts the distribution of objects of different scales by resampling the input images at low magnification, thereby enhancing the ability of small object detection;2) we design a Global Proposal Contrast Consistency Loss (GPCC), which can enhance the intra-class compactness and inter-class diversity of Region of Interest (RoI) features, thereby reducing the class inconsistency in pseudo-labels;and 3) we adopt a loss blending optimization strategy, which optimizes the localization accuracy of pseudo-labels by combining supervised loss and unsupervised loss. We conduct extensive experiments on multiple datasets, and the results show that SGPC significantly outperforms the latest other methods on the SSOD task. On the PASCAL VOC dataset, SGPC achieves 55.90 mAP, on the MS-COCO dataset, SGPC exceeds the supervised methods by more than 10 mAP at different scales, and we also verify the significant improvement and robustness of SGPC on the small object detection datasets VisDrone-2019 and EDD.

关键词： Proposals object detection Training Optimization Accuracy Location awareness Contrastive learning semi-supervised object detection comparative learning scale-rebalanced global proposal consistency comparison

来源：评论

学校读者我要写书评

暂无评论

DRCO: Dense-Label Refinement and Cross Optimization for semi-supervised object detection

引用

IEEE ACCESS 2025年 13卷 3572-3582页

作者： Qin, Yunlong Li, Yanjun Ji, Feifan Liu, Yan Wang, Yu Xiang, Ji Hangzhou City Univ Sch Informat & Elect Engn Hangzhou 310015 Peoples R China Zhejiang Univ Coll Control Sci & Engn Hangzhou 310027 Peoples R China Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China

In semi-supervised object detection (SSOD), the methods based on dense pseudo-labeling bypass complex post-processing while maintaining competitive performance compared to the methods based on sparse pseudo-labeling. However, there are still relatively few researches focused on the dense pseudo-labeling paradigm. In this work, we first experimentally point out the shortcomings of current dense pseudo-labeling methods: 1) Low-quality sampling: the fixed threshold strategies can result in numerous false negatives and false positives. 2) Inconsistency between classification scores and localization quality: classification scores cannot represent localization quality, resulting in poor quality of predicted bounding boxes for sampled positive samples. 3) Suboptimal training approach: current training methods only utilize its knowledge from the perspective of final dense pseudo-labels, failing to fully exploit the teacher model. To address these issues, we propose a method called Dense-Label Refinement and Cross Optimization (DRCO) based on dense pseudo-labels. Specifically, to tackle the issue of low-quality sampling, we introduce the Adaptive Sampling Approach (ASA), which achieves high-quality sampling at the image level and dynamic sampling ratios without introducing any additional hyperparameters. For the inconsistency between classification scores and localization quality, Comprehensive FRS (cFRS) is proposed to jointly optimize the classification and localization branches more efficiently, thereby obtaining a more comprehensive score. Finally, for the suboptimal training approach, we introduce Cross Prediction Optimization (CPO). CPO efficiently leverages the knowledge of the teacher model through a Cross-Head operation, thereby achieving more effective teacher-student interaction. DRCO achieves 27.31% mAP with only 1% COCO labeled data, which is approximately 1.24% mAP higher than the previous state-of-the-art. Based on MS COCO and PASCAL VOC benchmarks, further co

关键词： Optimization Adaptation models Training object detection Predictive models Location awareness Data models Detectors Proposals Image classification semi-supervised object detection object detection semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A semi-supervised object detection Method for Close Range detection of Spacecraft and Space Debris

引用

INTERNATIONAL JOURNAL OF AERONAUTICAL AND SPACE SCIENCES 2025年第2期26卷 773-784页

作者： Zhang, Huan Zhang, Yang Feng, Qingjuan Zhang, Kebei Beijing Informat Sci & Technol Univ Beijing 100192 Peoples R China Beijing Inst Control Engn Beijing 100094 Peoples R China

With the continuous development of space missions, a large number of artificial objects have been produced and deployed in Earth orbit, and there is an urgent need to equip satellites with the ability to autonomously detect nearby space targets to cope with the harm caused by non-cooperative targets to the safety of in orbit satellites. To meet the needs of intelligent detection of spacecraft and space debris, we propose a semi supervised target detection method with domain generalization capability. This method aims to improve the detection methods for spacecraft and debris, utilizing limited labeled data and a large amount of unlabeled data to train end-to-end networks and reduce dependence on data labeled information. In the semi-supervised Learning framework, we optimized and improved the dense detection network model, enhanced the Receptive field of the model, and optimized the feature fusion and representation capabilities of the model. The improved semi supervised object detection algorithm trained with only 10% annotation information achieved an mAP@0.50:0.95 metric of 69.2% on the SPARK space object detection data set, which is superior to object detection algorithms such as Fast R-CNN that utilize 100% annotation information. In addition, a fast image style transfer similar to target domain image augmentation method has been introduced to address the challenge of model domain generalization. The addition of generated style transfer images in the semi supervised method enhances the model's generalization ability towards the target domain, thereby improving the detection performance of the target domain.

关键词： Space object detection semi-supervised object detection Domain generalization

来源：评论

学校读者我要写书评

暂无评论

Elaborate Teacher: Improved semi-supervised object detection With Rich Image Exploiting

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 11345-11357页

作者： Yang, Xi Zhou, Qiubai Wei, Ziyu Liu, Hong Wang, Nannan Gao, Xinbo Xidian Univ Sch Telecommun Engn State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Fourth Mil Med Univ Dept Biomed Engn Xian 710032 Peoples R China Fourth Mil Med Univ Shaanxi Key Lab Bioelectromagnet Detect & Intellig Xian 710032 Peoples R China Space Engn Univ Space Secur Res Ctr Beijing 101400 Peoples R China Xidian Univ Sch Elect Engn Xian 710071 Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Image Cognit Chongqing Peoples R China

semi-supervised object detection (SSOD) has shown remarkable results by leveraging image pairs with a teacher-student framework. An excellent strong augmentation method can generate richer images and alleviate the influence of noise in pseudo-labels. However, existing data augmentation methods for SSOD do not consider instance-level information, thus, they cannot make full use of unlabeled data. Besides, the current teacher-student framework in SSOD solely relies on pseudo-labeling techniques, which may disregard some uncertain information. In this article, we introduce a new method called Elaborate Teacher which generates and exploits image pairs in a more refined manner. To enrich strongly augmented images, a novel data augmentation method called Information-Aware Mixup Representation (IAMR) is proposed. IAMR utilizes the teacher model's predictions as prior information and considers instance-level information, which can be seamlessly integrated with existing SSOD data augmentation methods. Furthermore, to fully exploit the information in unlabeled data, we propose the Enhanced Scale Consistency Regularization (ESCR), which considers the consistency from both semantic space and feature space. Elaborate Teacher introduces a fresh data augmentation method, complemented by consistency regularization, which boosts the performance of semi-supervised object detectors. Extensive experiments on the PASCAL VOC and MS-COCO datasets demonstrate the effectiveness of our method in leveraging unlabeled image information. Our method consistently outperforms the baseline method and improves mAP by 11.6% and 9.0% relative to the supervised baseline method when using 5% and 10% of labeled data on MS-COCO, respectively.

关键词： object detection Data augmentation Data models Semantics Task analysis Predictive models semisupervised learning Consistency regularization pseudo-labeling semi-supervised object detection teacher-student framework

来源：评论

学校读者我要写书评

暂无评论

CREDIBLE TEACHER FOR semi-supervised object detection IN OPEN SCENE 49

CREDIBLE TEACHER FOR SEMI-SUPERVISED OBJECT DETECTION IN OPE...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhuang, Jingyu Wang, Kuo Lin, Liang Li, Guanbin Sun Yat Sen Univ Guangzhou Peoples R China Sun Yat Sen Univ Shenzhen Sch Comp Sci & Engn Res Inst Shenzhen Peoples R China

ISBN: (纸本)9798350344868;9798350344851

semi-supervised object detection (SSOD) has achieved resounding success by leveraging unlabeled data to improve detection performance. However, in Open Scene semi-supervised object detection (O-SSOD), unlabeled data may contains unknown objects not observed in the labeled data, which will increase uncertainty in the model's predictions for known objects. It is detrimental to the current methods that mainly rely on self-training, as more uncertainty leads to the lower localization and classification precision of pseudo labels. To this end, we propose Credible Teacher, an end-to-end framework. Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels. Empirical results have demonstrated our method effectively restrains the adverse effect caused by O-SSOD and significantly outperforms existing counterparts.

关键词： semi-supervised object detection

来源：评论

学校读者我要写书评

暂无评论

Dense Pseudo-Labels based semi-supervised object detection for Remote Sensing

Dense Pseudo-Labels based Semi-supervised Object Detection f...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ma, Yongjie Lan, Shiyong Ma, Wei Yin, Xiaoxiao Li, Yao Sichuan Univ Chengdu Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Deep-learning-based object detection has recently played an increasingly important role in analyzing geographic spatial information. However, object detection performance is strongly correlated with the quality and quantity of manually labeled data. Furthermore, object detection in Remote Sensing differs from natural scenes and faces two challenges: 1) Dense instance distribution and 2) Significant scale variations. These issues also contribute to the difficulty of manual annotation. To this end, based on a dense pseudo-labeling framework and multi-scale learning, this paper proposes a novel semi-supervised object detection (SSOD) framework for remote sensing, namely RemoteDPL. Firstly, a fusion module is proposed to adaptively integrate spatial and channel features of images at different scales, improving the detection of objects at various scales. Second, a specialized branch predicts instance density and aids in pseudo-label mining to enhance detection in dense scenarios. Finally, a two-stage filtering strategy is devised for pseudo-label mining, which first filters to obtain the "pending" class prediction boxes and then further filters this portion of prediction boxes to obtain the pseudo-labels according to the joint confidence based on the classification and density scores. Extensive experiments on DOTA-v1.0 have demonstrated that our proposed RemoteDPL surpasses the current state-of-the-art SSOD methods in various semi-supervised settings.

关键词： semi-supervised object detection Remotesensing images Multi-scale learning Multi-scale feature fusion Pseudo-label mining

来源：评论

学校读者我要写书评

暂无评论

semi-supervised object detection FRAMEWORK WITH object FIRST MIXUP FOR REMOTE SENSING IMAGES

SEMI-SUPERVISED OBJECT DETECTION FRAMEWORK WITH OBJECT FIRST...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Zhang, Ziyu Feng, Zhixi Yang, Shuyuan Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China

ISBN: (纸本)9781665403696

This paper proposes a Simple semi-supervised object detection framework for Remote Sensing images, which is named SSOD-RS. SSOD-RS contains two parts, improved self-raining and consistency regularization based on strong data augmentations with improved mixup. Firstly, as an augmentation algorithm, object First mixup (OF-mixup) is proposed to adjust the weight of objects and the background, which expands the distribution of training samples while reducing the interference of the remote sensing complex background to the features of objects. Secondly, the strategy of training with assembling loss and fine-tuning is introduced into self-training to make the model fit the feature distribution of the true-labels after learning the features from the pseudo-labels. Experimental results demonstrate that SSOD-RS making use of unlabeled images can significantly improve the accuracy of the model.

关键词： object First mixup semi-supervised object detection self-training remote sensing fine-turning

来源：评论

学校读者我要写书评

暂无评论

Temporal Self-Ensembling Teacher for semi-supervised object detection

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2022年 24卷 3679-3692页

作者： Chen, Cong Dong, Shouyang Tian, Ye Cao, Kunlin Liu, Li Guo, Yuanhao Keya Med Technol Shenzhen 518116 Peoples R China Cambricon Software Dept Beijing 100010 Peoples R China Tencent Hippocrates Res Lab Shenzhen 518052 Peoples R China Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China Univ Oulu Ctr Machine Vis & Signal Anal Oulu 90570 Finland Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China

This paper focuses on the semi-supervised object detection (SSOD) which makes good use of unlabeled data to boost performance. We face the following obstacles when adapting the knowledge distillation (KD) framework in SSOD. (1) The teacher model serves a dual role as a teacher and a student, such that the teacher predictions on unlabeled images may limit the upper bound of the student. (2) The data imbalance issue caused by the large quantity of consistent predictions between the teacher and student hinders an efficient knowledge transfer between them. To mitigate these issues, we propose a novel SSOD model called Temporal Self-Ensembling Teacher (TSET). Our teacher model ensembles its temporal predictions for unlabeled images under stochastic perturbations. Then, our teacher model ensembles its model weights with those of the student model by an exponential moving average. These ensembling strategies ensure data and model diversity, and lead to better teacher predictions for unlabeled images. In addition, we adapt the focal loss to formulate the consistency loss for handling the data imbalance issue. Together with a thresholding method, the focal loss automatically reweights the inconsistent predictions, which preserves the knowledge for difficult objects to detect in the unlabeled images. The mAP of our model reaches 80.73% and 40.52% on the VOC2007 test set and the COCO2014 minival5k set, respectively, and outperforms a strong fully supervised detector by 2.37% and 1.49%, respectively. Furthermore, the mAP of our model (80.73%) sets a new state-of-the-art performance in SSOD on the VOC2007 test set.

关键词： object detection Predictive models Training Detectors Data models Analytical models Transforms semi-supervised object detection deep convolutional neural networks knowledge distillation temporal self-ensembling focal loss

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：