检索结果-内蒙古大学图书馆

PA-WSDIS: A prior-aware weakly supervised defect instance segmentation model for car body surface

ADVANCED ENGINEERING INFORMATICS 2025年 65卷

作者： He, Yike Wang, Yueming Jiang, Weiwei Hu, Songyu Fu, Jianzhong Zhejiang Univ Coll Mech Engn State Key Lab Fluid Power & Mechatron Syst Hangzhou 310027 Peoples R China Zhejiang Univ Coll Mech Engn Key Lab Printing Proc & Equipment Zhejiang Prov 3D Hangzhou 310027 Peoples R China Zhejiang Univ Polytech Inst Hangzhou 310027 Peoples R China Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China

Car body surface defect instance segmentation is essential for ensuring product quality and setting precise size thresholds for defects during product inspection process. However, few defect instance segmentation applications has been found in industrial scenarios until now. This is due in large part to the fact that the pixel-level annotation of defects is cumbersome and labor-intensive. Although various weakly supervised methods have shown promising results, they usually lack the ability to fully explore prior information and the awareness of hierarchical semantic correlations, thereby limiting the defect instance segmentation performance. To address this issue, we propose a novel prior-aware weakly supervised defect instance segmentation (PA-WSDIS) model for car body surface, removing the need for pixel-level labeling. First, we design a box-driven coarse mask generator to obtain coarse masks, which serve as potential proposals for the subsequent refinement process. Then, we propose a boundary guided prior constraint loss, consisting of boundary alignment and pixel-pair similarity mining losses, to fully leverage prior information to enhance the discriminative ability and provide reliable refinement guidance for the model. Finally, we propose a correlative semantic calibration loss, which comprehensively perceives the rich semantic features of different dimensions from both local and global perspectives. With the collaborative constraints of these meticulously designed loss functions, precise instance segmentation results are achieved. Experimental results showcase the outstanding performance of the PA-WSDIS model with an impressive 87.4% 50 , which is considerably superior to state-of-the-art methods. As far as we know, our proposed method is the first weakly supervised instance segmentation model based on bounding box labels for industrial defect detection tasks.

关键词： Defect detection instance segmentation Weakly supervised learning Car body surface

来源：评论

学校读者我要写书评

暂无评论

SAF-IS: A spatial annotation free framework for instance segmentation of surgical tools

引用

MEDICAL IMAGE ANALYSIS 2025年 101卷 103471页

作者： Sestini, Luca Rosa, Benoit De Momi, Elena Ferrigno, Giancarlo Padoy, Nicolas Univ Strasbourg ICube CNRS Strasbourg France Politecn Milan Dept Elect Informat & Bioengn Milan Italy IHU Strasbourg Strasbourg France

instance segmentation of surgical instruments is a long-standing research problem, crucial for the development of many applications for computer-assisted surgery. This problem is commonly tackled via fully-supervised training of deep learning models, requiring expensive pixel-level annotations to train. In this work, we develop a framework for instance segmentation not relying on spatial annotations for training. Instead, our solution only requires binary tool masks, obtainable using recent unsupervised approaches, and tool presence labels, freely obtainable in robot-assisted surgery. Based on the binary mask information, our solution learns to extract individual tool instances from single frames, and to encode each instance into a compact vector representation, capturing its semantic features. Such representations guide the automatic selection of a tiny number of instances (8 only in our experiments), displayed to a human operator for tool-type labelling. The gathered information is finally used to match each training instance with a tool presence label, providing an effective supervision signal to train a tool instance classifier. We validate our framework on the EndoVis 2017 and 2018 segmentation datasets. We provide results using binary masks obtained either by manual annotation or as predictions of an unsupervised binary segmentation model. The latter solution yields an instance segmentation approach completely free from spatial annotations, outperforming several state-of-the-art fully-supervised segmentation approaches.

关键词： Endoscopic videos instance segmentation Tool segmentation Weakly supervised learning Self supervised learning

来源：评论

学校读者我要写书评

暂无评论

Amodal instance segmentation with dual guidance from contextual and shape priors

引用

APPLIED SOFT COMPUTING 2025年 169卷

作者： Zhan, Jiao Luo, Yarong Guo, Chi Wu, Yejun Yang, Bohan Wang, Jingrong Liu, Jingnan Wuhan Univ GNSS Res Ctr Wuhan 430072 Hubei Peoples R China Hubei Luojia Lab Wuhan 430079 Hubei Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China

Human perception possesses the remarkable ability to mentally reconstruct the complete structure of occluded objects, which has inspired researchers to pursue amodal instance segmentation for a more comprehensive understanding of the scene. Previous works have shown promising results, but they often capture the contextual dependencies in an unsupervised way, which can lead to undesirable contextual dependencies and unreasonable feature representations. To tackle this problem, we propose a Pixel Affinity-Parsing (PAP) module trained with the Pixel Affinity Loss (PAL). Embedded into CNN, the PAP module can leverage learned contextual priors to guide the network to explicitly distinguish different relationships between pixels, thus capturing the intraclass and inter-class contextual dependencies in a non-local and supervised way. This process helps to yield robust feature representations to prevent the network from misjudging. To demonstrate the effectiveness of the PAP module, we design an effective Pixel Affinity-Parsing Network (PAPNet). Notably, PAPNet also introduces shape priors to guide the amodal mask refinement process, thus preventing implausible shapes in the predicted masks. Consequently, with the dual guidance of contextual and shape priors, PAPNet can reconstruct the full shape of occluded objects accurately and reasonably. Experimental results demonstrate that the proposed PAPNet outperforms existing state-of-the-art methods on multiple amodal datasets. Specifically, on the KINS dataset, PAPNet achieves 37.1% AP, 60.6% AP50 and 39.8% AP75, surpassing C2F-Seg by 0.6%, 2.4% and 2.8%. On the D2SA dataset, PAPNet achieves 71.70% AP, 85.98% AP50 and 77.10% AP75, surpassing PGExp by 0.75% and 0.33% in AP50 and AP75, and being comparable to PGExp in AP. On the COCOA-cls dataset, PAPNet achieves 41.29% AP, 60.95% AP50 and 46.17% AP75, surpassing PGExp by 3.74%, 3.21% and 4.76%. On the CWALT dataset, PAPNet achieves 72.51% AP, 85.02% AP50 and 80.47% AP75, surpass

关键词： instance segmentation Amodal instance segmentation Pixel affinity Contextual dependency

来源：评论

学校读者我要写书评

暂无评论

iShapeInst: A novel and effective instance segmentation for irregularly shaped objects

引用

NEUROCOMPUTING 2025年 638卷

作者： Wang, Yang Zhou, Wanlin Zhou, Jiakai Anhui Univ Technol Sch Mech Engn Maanshan 243000 Peoples R China Anhui Prov Key Lab Special Heavy LoadRobot Maanshan 243000 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Mech & Elect Engn Nanjing 210000 Peoples R China

instance segmentation of irregularly shaped objects presents significant challenges. Existing methods struggle to generate accurate representations for such objects, leading to suboptimal segmentation performance. This study introduces iShapeInst, a novel region-based instance segmentation method designed to address these challenges. iShapeInst dynamically generates convolution kernels based on the position and shape to represent the irregular objects. Specifically, the method begins by using semantic segmentation to predict the regions of all objects and generates multiple convolution kernels corresponding to these regions. Then, metric learning is employed to cluster the kernels for the same instance while separating between different instances. Additionally, kernel fusion is utilized to select high-quality kernels for each instance, reducing resource consumption. instance masks are subsequently created by convolving the mask feature map with these high-quality kernel weights. Finally, an optimal instance mask is derived using Matrix NMS. Experiments demonstrate that iShapeInst achieves an mAP (mean Average Precision) of 85.2% on the iShape dataset, outperforming existing methods by 13.5% mAP, with a processing speed of 31.5 FPS. Furthermore, our method achieves competitive performance on the Surgical Instruments Dataset and arbitrary-shaped scene text datasets, demonstrating its strong generalization capability. The code is available at https://***/youngnuaa/ iShapeInst.

关键词： Irregularly shaped object Kernel weight Metric learning Kernel fusion instance segmentation

来源：评论

学校读者我要写书评

暂无评论

Supervoxel-Based instance segmentation of Pole-Like Facilities From Mobile Laser Scanning Data Using Pyramid Cascaded Fisher Vector Modeling

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Ye, Longjie Xiao, Wen Weng, Qihao Hong Kong Polytech Univ Res Ctr Artificial Intelligence Geomatics Dept Land Surveying & Geoinformat JC STEM Lab Earth Observat Hong Kong Peoples R China China Univ Geosci Natl Engn Res Ctr Geog Informat Syst Sch Geog & Informat Engn Wuhan 430074 Peoples R China

Efficient and automatic object recognition in road scenes plays an essential role in smart city applications such as autonomous driving and intelligent infrastructure. As an important component of road scenes, pole-like facilities (PLFs) have been challenging to recognize high-definition road mapping. To achieve the automatic recognition of PLFs from cluttered mobile laser scanning (MLS) data, a novel instance segmentation method is proposed. First, candidate poles are detected by a supervoxel-based histogram analysis from partitioned off-ground point clouds. Then, instance segmentation of PLFs is achieved through a constrained hierarchical region-growing algorithm based on voxelized point clouds. A pyramid cascaded Fisher vector (FV) model and a random forest (RF) classifier are applied to classify the delineated pole-like road facilities into six predefined categories: trees, traffic signs, traffic lights, lamps, bare poles, and other objects. The proposed method is tested on three datasets collected in street scenes with different types of road facilities and point densities. Results demonstrate that our method can effectively achieve instance segmentation of PLFs in complex road environments. The proposed method outperformed state of the art for PLF detection in correctness (93.5%), completeness (95.3%), and quality (88.81%). Besides, the proposed method achieved satisfactory results for instance-level semantic segmentation with an average F1 score of 90.2%, demonstrating the effectiveness of geometric information enhancement in the designed FV coding approach.

关键词： Roads instance segmentation Point cloud compression Accuracy Shape Feature extraction Random forests Semantics Training Object recognition High-definition urban mapping instance segmentation mobile laser scanning (MLS) pole-like objects roadside facility smart city smart traffic supervoxels

来源：评论

学校读者我要写书评

暂无评论

Amodal instance segmentation for Mealworm Growth Monitoring Using Synthetic Training Images

引用

IEEE ACCESS 2025年 13卷 52157-52175页

作者： Dolata, Przemyslaw Majewski, Pawel Lampa, Piotr Zieba, Maciej Reiner, Jacek Wroclaw Univ Sci & Technol Dept Artificial Intelligence PL-50372 Wroclaw Poland Wroclaw Univ Sci & Technol Fac Informat & Commun Technol PL-50370 Wroclaw Poland Wroclaw Univ Sci & Technol Fac Mech Engn PL-50370 Wroclaw Poland Tooploox PL-53601 Wroclaw Poland

Automatic dimensioning of mealworms based on computer vision is challenging due to occlusions. Amodal instance segmentation (AIS) could be a viable solution, but the acquisition of annotated training data is difficult and time-consuming. This work proposes a new method to prepare data for training AIS models that reduces the human annotation effort significantly. Instead of acquiring the occluded images directly, only images of fully visible larvae are acquired and processed, allowing obtaining their contours via automatic segmentation. Next, synthetic images with occlusions are generated from the database of automatically extracted instances. The generation procedure uses simple computer graphics tools and is computationally inexpensive, yet yields images that allow training off-the-shelf AIS models. Since those models need to be tested on real data, which requires manual annotation, a data acquisition method that significantly simplifies the test set annotation process is demonstrated. Results are reported in terms of the amodal segmentation quality as well as the accuracy of larvae dimensioning, measured using the histogram intersection metric. The best-performing model achieves a mean average precision of 0.41 and a histogram intersection of 0.77, confirming the effectiveness of the proposed method of data acquisition and generation. The method is not specific to mealworm detection and could be applied to other similar problems where object occlusions pose a challenge.

关键词： Annotations Image segmentation Artificial intelligence Training Data models Object segmentation Training data Three-dimensional displays Shape Amodal segmentation instance segmentation dense scenes dataset synthesis synthetic images Tenebrio molitor Tenebrio molitor

来源：评论

学校读者我要写书评

暂无评论

SGIFormer: Semantic-Guided and Geometric-Enhanced Interleaving Transformer for 3D instance segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第3期35卷 2276-2288页

作者： Yao, Lei Wang, Yi Liu, Moyun Chau, Lap-Pui Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China

In recent years, transformer-based models have exhibited considerable potential in point cloud instance segmentation. Despite the promising performance achieved by existing methods, they encounter challenges such as instance query initialization problems and excessive reliance on stacked layers, rendering them incompatible with large-scale 3D scenes. This paper introduces a novel method, named SGIFormer, for 3D instance segmentation, which is composed of the Semantic-guided Mix Query (SMQ) initialization and the Geometric-enhanced Interleaving Transformer (GIT) decoder. Specifically, the principle of our SMQ initialization scheme is to leverage the predicted voxel-wise semantic information to implicitly generate the scene-aware query, yielding adequate scene prior and compensating for the learnable query set. Subsequently, we feed the formed overall query into our GIT decoder to alternately refine instance query and global scene features for further capturing fine-grained information and reducing complex design intricacies simultaneously. To emphasize geometric property, we consider bias estimation as an auxiliary task and progressively integrate shifted point coordinates embedding to reinforce instance localization. SGIFormer attains state-of-the-art performance on ScanNet V2, ScanNet200, S3DIS datasets, and the challenging high-fidelity ScanNet ++ benchmark, striking a balance between accuracy and efficiency. The code, weights, and demo videos are publicly available at https://***/SGIFormer/.

关键词： Three-dimensional displays Semantics instance segmentation Decoding Point cloud compression Pipelines Feature extraction Accuracy Training Point clouds 3D instance segmentation transformer semantic features semantic features

来源：评论

学校读者我要写书评

暂无评论

A teacher-student framework leveraging large vision model for data pre-annotation and YOLO for tunnel lining multiple defects instance segmentation

引用

JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION 2025年 44卷

作者： Yang, Hanlong Wang, Lujie Pan, Yue Chen, Jin-Jian Shanghai Jiao Tong Univ Dept Civil Engn State Key Lab Ocean Engn Shanghai Key Lab Digital Maintenance Bldg & Infras 800 Dongchuan Rd Shanghai 200240 Peoples R China Tongji Univ Dept Geotech Engn Shanghai 200092 Peoples R China Shanghai Shentong Metro Grp Co Ltd Shanghai 20070 Peoples R China

To achieve an accurate and efficient instance segmentation task for multiple defects within tunnel linings, this paper proposes a simple yet powerful Teacher-Student Framework (TeSF) leveraging the emerging Large Vision Model (LVM) and the advanced You Only Look Once v5 (YOLO v5) model. TeSF integrates a pre-trained LVM within the Teacher Module to alleviate data annotation efforts. Concurrently, the Student Module introduces a novel top-down model architecture, amalgamating YOLO v5 for top-level Classification & Localization and a Segment Head for down-level segmentation, resulting in YOLO-SH. The Teacher Module acts as a data engine for automatic learning in the Student Module through a well-designed loss function. The proposed TeSF is tested in images collected from Shanghai metro tunnels to automatically recognize five different types of tunnel surface defects. Experiment results indicate that: (1) The LVM-based data annotation procedure in the Teacher Module surpasses the efficacy of the traditional manual method. (2) Optimal equilibrium between computational efficiency and segmentation accuracy is achieved with a medium-sized backbone for YOLO v5, yielding mask mAP@0.5 values of 0.644 and 0.694, all within an inference time of 6.2ms/image. (3) The top-down Student Module with YOLO-SH v5m exhibits superior performance in instance segmentation compared to state-of-the-art models, bringing improvements of no less than 8.2% and 6.3% in box mAP@0.5 and mask mAP@0.5, respectively. In short, the novelty of TeSF lies in the utilization of the pre-trained LVM for streamlined data annotation coupled with the augmentation of YOLO-SH for a more cost-effective and precise detection of multiple defects within tunnels. The applicability of TeSF can extend to the analysis of 3D scanner images derived from in-service tunnel environments.

关键词： instance segmentation Multiple defects detection Large vision model You Only Look Once (YOLO) Metro tunnel

来源：评论

学校读者我要写书评

暂无评论

YOLO-ITC: A New YOLO Method for instance segmentation of Individual Tree Crowns

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年

作者： Sun, Ziyi Xue, Bing Zhang, Mengjie Schindler, Jan Victoria Univ Wellington Ctr Data Sci & Artificial Intelligence Wellington 6140 New Zealand Victoria Univ Wellington Sch Engn & Comp Sci Wellington 6140 New Zealand Manaaki Whenua Landcare Res Wellington 6140 New Zealand

The instance segmentation task of individual tree crowns is an important real-world application that facilitates forest management, carbon storage estimation, and biodiversity modelling. Recently, Convolutional Neural Networks (CNNs) have achieved great success in computer vision. Several efforts have applied CNNs to perform instance segmentation of tree canopies. However, the existing CNN works rarely consider instance segmentation and species classification of densely distributed small and medium tree crowns. YOLO, as a fast and effective method, shows promising results in the field of instance segmentation and canopy detection and segmentation. We utilize a tree crown dataset from Wellington, Aotearoa, New Zealand, based on aerial imagery which contains small and medium-sized tree objects distributed across a diverse rural landscape ranging from isolated trees to dense forest stands. We propose a new YOLO method for individual tree crowns (ITC) based on YOLOv7, named YOLO-ITC. Specifically, a new detection design targeting small and medium trees is first proposed. Based on this, we propose a Dense Block module for the main block of the backbone in a densely connected way, where the previous features are reused to aggregate more useful information. Finally, efficient attention is embedded in the Dense Block to capture the globally long-range dependencies. Extensive experimental results show that the proposed method, YOLO-ITC, achieves both higher detection and mask accuracy over other commonly used baseline models.

关键词： Vegetation instance segmentation Feature extraction YOLO Neck Forestry Head Accuracy Sun Proposals tree crowns tree species

来源：评论

学校读者我要写书评

暂无评论

A Novel Shape Guided Transformer Network for instance segmentation in Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 8325-8339页

作者： Yu, Dawen Ji, Shunping Fuzhou Univ Acad Digital China Key Lab Spatial Data Min & Informat Sharing Minist Educ Fuzhou 350108 Peoples R China Wuhan Univ Sch Remote Sensing Informat Engn Wuhan 430079 Peoples R China

instance segmentation performance in remote sensing images (RSIs) is significantly affected by two issues: how to extract accurate boundaries of objects from remote imaging through the dynamic atmosphere, and how to integrate the mutual information of related object instances scattered over a vast spatial region. In this study, we propose a novel shape guided transformer network (SGTN) to accurately extract objects at the instance level. Inspired by the global contextual modeling capacity of the self-attention mechanism, we propose an effective transformer encoder termed LSwin, which incorporates vertical and horizontal 1-D global self-attention mechanisms to obtain better global-perception capacity for RSIs than the popular local-shifted-window based swin transformer. To achieve accurate instance mask segmentation, we introduce a shape guidance module (SGM) to emphasize the object boundary and shape information. The combination of SGM, which emphasizes the local detail information, and LSwin, which focuses on the global context relationships, achieve excellent RSI instance segmentation. Their effectiveness was validated through comprehensive ablation experiments. Especially, LSwin is proven better than the popular ResNet and swin transformer encoders at the same level of efficiency. Compared to other instance segmentation methods, our SGTN achieves the highest average precision scores on two single-class public datasets (WHU dataset and BITCC dataset) and a multiclass public dataset (NWPU VHR-10 dataset).

关键词： Transformers Shape instance segmentation Computational modeling Remote sensing Correlation Feature extraction Accuracy Recurrent neural networks Convolution long-range correlation remote sensing image (RSI) shape enhancement transformer network

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：