检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhu, Hui Lu, Yongchun Zhao, Hongyu Zhao, Guoqing Zhao, Xiaofang Chinese Academy of Sciences Institute of Computing Technology China University of Chinese Academy of Sciences China Mashang Consumer Finance Co. Ltd China Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou China

ISBN: (纸本)9781728163277

semi-supervised object detection (SSOD) is a significant application of semi-supervised learning to further improve object detectors but suffers more seriously from confirmation bias and error accumulation caused by the classes imbalance. Existing SSOD approaches have attempted to address this issue but fails to consider dynamically changed detection difficulties of different classes for detectors. In this paper, we propose adaptively focus-aware confidence, which treats object classes differently. Predictions generated from the teacher and student models are stored in a memory dictionary, and the differences between them are utilized to adaptively perceive learning statuses. Based on this, confidence thresholds are flexibly assigned and adjusted for different classes. Extensive experiments are conducted on MS-COCO benchmark dataset with multiple protocols and our SSOD framework out-performs the state-of-the-art competitors by a large margin. © 2023 IEEE.

关键词： Adaptive confidence threshold Learning status Memory dictionary semi-supervised object detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic balanced teacher: A semi-supervised object detection algorithm for train faults

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 138卷

作者： Sun, Guodong Pan, Xingyu Liang, Qihang Wu, Bo Hubei Univ Technol Sch Mech Engn Wuhan 430068 Peoples R China Chinese Acad Sci Shanghai Adv Res Inst Shanghai 201210 Peoples R China

Efficient visual fault detection in freight trains is crucial for guaranteeing the safety of rail transportation. At present, deep learning-based methods for diagnosing faults in freight trains necessitate substantial amounts of labeled data for training. However, the procurement of this labeled data is both costly and timeconsuming, posing significant challenges for the practical implementation of these methods. In this study, we propose a semi-supervised fault detection algorithm that demands fewer labeled data, while maintaining detection accuracy. Initially, we employ a lightweight vision transformer for feature extraction to minimize computational requirements in the detector. Subsequently, we implement Dynamic Label Assignment to replace the static-based Intersection over Union strategy, thereby enhancing the robustness of the teacher-student network against noise pseudo-frames. Lastly, we establish a balanced learning framework that effectively mitigates sample-level and target-level imbalances during training. We conduct extensive experiments on three faulty datasets, and the results demonstrate that our method surpasses alternative approaches at various labeling ratios(i.e. 1%, 2%, 5%, 10%).

关键词： Fault detection Freight train images semi-supervised object detection Dynamic training

来源：评论

学校读者我要写书评

暂无评论

Improving Localization for semi-supervised object detection 21st

Improving Localization for Semi-Supervised Object Detection

引用

21st International Conference on Image Analysis and Processing (ICIAP)

作者： Rossi, Leonardo Karimi, Akbar Prati, Andrea Univ Parma IMP Lab DIA Parma Italy

ISBN: (纸本)9783031064302;9783031064296

Nowadays, semi-supervised object detection (SSOD) is a hot topic, since, while it is rather easy to collect images for creating a new dataset, labeling them is still an expensive and time-consuming task. One of the successful methods to take advantage of raw images on a semi-supervised Learning (SSL) setting is the Mean Teacher technique [17], where the operations of pseudo-labeling by the Teacher and the Knowledge Transfer from the Student to the Teacher take place simultaneously. However, the pseudo-labeling by thresholding is not the best solution since the confidence value is not strictly related to the prediction uncertainty, not permitting to safely filter predictions. In this paper, we introduce an additional classification task for bounding box localization to improve the filtering of the predicted bounding boxes and obtain higher quality on Student training. Furthermore, we empirically prove that bounding box regression on the unsupervised part can equally contribute to the training as much as category classification. Our experiments show that our IL-net (Improving Localization net) increases SSOD performance by 1.14% AP on COCO dataset in limited-annotation regime. The code is available at https://***/IMPLabliniPriunbiasedteacher/tree/ilnet.

关键词： object detection Multi-task learning Teacher-student technique semi-supervised learning semi-supervised object detection

来源：评论

学校读者我要写书评

暂无评论

Diverse Learner: Exploring Diverse Supervision for semi-supervised object detection 17th

Diverse Learner: Exploring Diverse Supervision for Semi-supe...

引用

17th European Conference on Computer Vision (ECCV)

作者： Li, Linfeng Jiang, Minyue Yu, Yue Zhang, Wei Lin, Xiangru Li, Yingying Tan, Xiao Wang, Jingdong Ding, Errui Baidu Inc Beijing Peoples R China Natl Univ Singapore Singapore Singapore

ISBN: (纸本)9783031200557;9783031200564

Current state-of-the-art semi-supervised object detection methods (SSOD) typically adopt the teacher-student framework featured with pseudo labeling and Exponential Moving Average (EMA). Although the performance is desirable, many remaining issues still need to be resolved, for example: (1) the teacher updated by the student using EMA tends to lose its distinctiveness and hence generates similar predictions comparing with student and causes potential noise accumulation as the training proceeds;(2) the exploitation of pseudo labels still has much room for improvement. We present a diverse learner semi-supervised object detection framework to tackle these issues. Concretely, to maintain distinctiveness between teachers and students, our framework consists of two paired teacher-student models with diverse supervision strategy. In addition, we argue that the pseudo labels which are typically regarded as unreliable and obsoleted by many existing methods are of great value. A particular training strategy consisting of Multi-threshold Classification Loss (MTC) and Pseudo Label-Aware Erasing (PLAE) is hence designed to well explore the full set of all pseudo labels. Extensive experimental results show that our diverse learner framework outperforms the previous state-of-the-art method on the MS-COCO dataset by 2.10%, 1.50% and 0.83% when training with only 1%, 5% and 10% labeled data, demonstrating the effectiveness of our proposed framework. Moreover, our approach also performs well with larger amount of data, e.g. using full COCO training set and 123K unlabeled images from COCO, reaching a new state-of-the-art performance of 44.86% mAP.

关键词： semi-supervised object detection Diverse learner Multi-threshold loss Pseudo label-aware erasing

来源：评论

学校读者我要写书评

暂无评论

Dense Teacher: Dense Pseudo-Labels for semi-supervised object detection 1

引用

17th European Conference on Computer Vision (ECCV)

作者： Zhou, Hongyu Ge, Zheng Liu, Songtao Mao, Weixin Li, Zeming Yu, Haiyan Sun, Jian MEGVII Technol Beijing Peoples R China Waseda Univ Tokyo Japan Harbin Inst Technol Harbin Peoples R China

ISBN: (数字)9783031200779

ISBN: (纸本)9783031200762;9783031200779

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the dense prediction as a united and straight forward form of pseudo-label. Compared to the pseudo-boxes, our Dense Pseudo-Label (DPL) does not involve any postprocessing method, thus retaining richer information. We also introduce a region selection technique to highlight the key information while suppressing the noise carried by dense labels. We name our proposed SSOD algorithm that leverages the DPL as Dense Teacher. On COCO and VOC, Dense Teacher shows superior performance under various settings compared with the pseudo-box-based methods. Code is available at https://***/Megvii- Basedetection/DenseTeacher.

关键词： semi-supervised object detection Dense pseudo-label

来源：评论

学校读者我要写书评

暂无评论

Lesion Localization in OCT by semi-supervised object detection 22

Lesion Localization in OCT by Semi-Supervised Object Detecti...

引用

ACM International Conference on Multimedia Retrieval (ICMR)

作者： Wu, Yue Zhou, Yang Zhao, Jianchun Yang, Jingyuan Yu, Weihong Chen, Youxin Li, Xirong Renmin Univ China Key Lab DEKE Beijing Peoples R China Beijing Visionary Intelligence Ltd Vistel AI Lab Beijing Peoples R China Peking Union Med Coll Hosp Dept Ophthalmol Beijing Peoples R China

ISBN: (纸本)9781450392389

Over 300 million people worldwide are affected by various retinal diseases. By noninvasive Optical Coherence Tomography (OCT) scans, a number of abnormal structural changes in the retina, namely retinal lesions, can be identified. Automated lesion localization in OCT is thus important for detecting retinal diseases at their early stage. To conquer the lack of manual annotation for deep supervised learning, this paper presents a first study on utilizing semi-supervised object detection (SSOD) for lesion localization in OCT images. To that end, we develop a taxonomy to provide a unified and structured viewpoint of the current SSOD methods, and consequently identify key modules in these methods. To evaluate the influence of these modules in the new task, we build OCT-SS, a new dataset consisting of over 1k expert-labeled OCT B-scan images and over 13k unlabeled B-scans. Extensive experiments on OCT-SS identify Unbiased Teacher (UnT) as the best current SSOD method for lesion localization. Moreover, we improve over this strong baseline, with mAP increased from 49.34 to 50.86.

关键词： OCT B-scan images retinal lesion localization semi-supervised object detection medical image analysis semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

semi-supervised Underwater object detection Using Grid Marker-Assisted Image Enhancement 17th

Semi-supervised Underwater Object Detection Using Grid Marke...

引用

17th International Conference on Intelligent Robotics and Applications

作者： Xia, Caixia Zhou, Wenzhang Zhang, Caiyu Fan, Baojie Nanjing Univ Posts & Telecommun Nanjing 210003 Peoples R China Univ Chinese Acad Sci Beijing 101408 Peoples R China

ISBN: (纸本)9789819607730;9789819607747

semi-supervised underwater object detection aims to obtain high-quality pseudo-labeled samples from an amount of unlabeled data, addressing the issue of missing data labels in underwater environments. In this work, we propose a grid marker-assisted image enhancement framework for semi-supervised underwater target detection (SSUTD-GMAIE). By analyzing the color distribution of unlabeled images in the color space grid, we guide balanced image enhancement to achieve semi-supervised underwater object detection. Specifically, we construct a 3D network based on the image color space, dividing the color space into several sub-regions. Each cubic region in the grid represents a certain range of color subspaces. Subsequently, we calculate the mean color values of all unlabeled images and statistically determine the probability of each cubic sample appearing in the grid. Meanwhile, we introduce a grid marker-assisted underwater image enhancement method. This method enhances training images based on network labeling information, sampling color information using random probabilities and sample distribution states, ensuring the authenticity of the enhanced images while reducing the color distribution difference between the enhanced images and the unlabeled images. This enhancement method is applied to the teacher-student model, achieving state-of-the-art performance on two semi-supervised underwater object detection benchmark datasets, demonstrating the effectiveness and superiority of our framework.

关键词： semi-supervised object detection Underwater Environments Image Enhancement

来源：评论

学校读者我要写书评

暂无评论

DENSITY-GUIDED DENSE PSEUDO LABEL SELECTION FOR semi-supervised ORIENTED object detection 31

DENSITY-GUIDED DENSE PSEUDO LABEL SELECTION FOR SEMI-SUPERVI...

引用

2024 International Conference on Image Processing

作者： Zhao, Tong Fang, Qiang Shi, Shuohao Xu, Xin Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha Peoples R China

ISBN: (纸本)9798350349405;9798350349399

Recently, dense pseudo-label, which directly selects pseudo labels from the original output of the teacher model without any complicated post-processing steps, has received considerable attention in semi-supervised object detection (SSOD). However, for the multi-oriented and dense objects that are common in aerial scenes, existing dense pseudo-label selection methods are inefficient because they ignore the significant density difference. Therefore, we propose Density-Guided Dense Pseudo Label Selection (DDPLS) for semi-supervised oriented object detection. In DDPLS, we design a simple but effective adaptive mechanism to guide the selection of dense pseudo labels. Specifically, we propose the Pseudo Density Score (PDS) to estimate the density of potential objects and use this score to select reliable dense pseudo labels. On the DOTA-v1.5 benchmark, the proposed method outperforms previous methods especially when labeled data are scarce. For example, it achieves 49.78 mAP given only 5% of annotated data, which surpasses previous state-of-the-art method given 10% of annotated data by 1.15 mAP. Our codes is available at https://***/Haru-zt/DDPLS.

关键词： semi-supervised object detection Oriented object detection Dense Pseudo-label

来源：评论

学校读者我要写书评

暂无评论

semi-supervised Method for Underwater object detection Algorithm Based on Improved YOLOv8

引用

APPLIED SCIENCES-BASEL 2025年第3期15卷 1065-1065页

作者： Xu, Siyi Wang, Jian Sang, Qingbing Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Peoples R China Jiangnan Univ Engn Res Ctr Intelligent Technol Healthcare Minist Educ Wuxi 214122 Peoples R China China Ship Sci Res Ctr Wuxi 214082 Peoples R China

Deep learning-based object detection technology is rapidly developing, and underwater object detection, an important subcategory, plays a crucial role in various fields such as underwater structure repair and maintenance, as well as marine scientific research. Some of the major challenges in underwater object detection are the relatively limited availability of underwater image and video datasets and the high cost of acquiring high-quality, diverse training data. To address this, we propose a novel underwater object detection method, SUD-YOLO, based on the Mean Teacher semi-supervised learning strategy. More specifically, it combines a small number of labeled samples with a large number of unlabeled samples, using the teacher model to guide the generation of pseudo-labels. In addition, a multi-scale pseudo-label enhancement module is developed specifically to address the issue of low-quality pseudo-labels. To overcome the model's difficulty in learning underwater image feature extraction, we integrate a receptive-field attention mechanism with local spatial features and then design a lightweight detection head based on the task alignment concept to further improve the model's feature extraction capability. Experimental results on the DUO dataset show that, by using only 10% of the labeled data, the proposed method achieves an average precision of 50.8, which is an improvement of 11.0% over the fully supervised YOLOv8 algorithm, 11.3% over the fully supervised YOLOv11 algorithm, 9.3% over the semi-supervised Efficient Teacher algorithm, and 3.4% on the semi-supervised Unbiased Teacher algorithm, while only 20% of the computational cost is required.

关键词： underwater object detection semi-supervised object detection receptive-field attention pseudo-labels

来源：评论

学校读者我要写书评

暂无评论

SAR-CDSS: A semi-supervised Cross-Domain object detection from Optical to SAR Domain

引用

REMOTE SENSING 2024年第6期16卷 940页

作者： Luo, Cheng Zhang, Yueting Guo, Jiayi Hu, Yuxin Zhou, Guangyao You, Hongjian Ning, Xia Aerosp Informat Res Inst Chinese Acad Sci Beijing 100094 Peoples R China Chinese Acad Sci Key Lab Technol Geospatial Informat Proc & Applica Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China

The unique imaging modality of synthetic aperture radar (SAR) has posed significant challenges for object detection, making it more complex to acquire and interpret than optical images. Recently, numerous studies have proposed cross-domain adaptive methods based on convolutional neural networks (CNNs) to promote SAR object detection using optical data. However, existing cross-domain methods focus on image features, lack improvement on input data, and ignore the valuable supervision provided by few labeled SAR images. Therefore, we propose a semi-supervised cross-domain object detection framework that uses optical data and few SAR data to achieve knowledge transfer for SAR object detection. Our method focuses on the data processing aspects to gradually reduce the domain shift at the image, instance, and feature levels. First, we propose a data augmentation method of image mixing and instance swapping to generate a mixed domain that is more similar to the SAR domain. This method fully utilizes few SAR annotation information to reduce domain shift at image and instance levels. Second, at the feature level, we propose an adaptive optimization strategy to filter out mixed domain samples that significantly deviate from the SAR feature distribution to train feature extractor. In addition, we employ Vision Transformer (ViT) as feature extractor to handle the global feature extraction of mixed images. We propose a detection head based on normalized Wasserstein distance (NWD) to enhance objects with smaller effective regions in SAR images. The effectiveness of our proposed method is evaluated on public SAR ship and oil tank datasets.

关键词： cross-domain synthetic aperture radar (SAR) semi-supervised object detection metric learning

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：