检索结果-内蒙古大学图书馆

Vanishing mask refinement in semi-supervised video object segmentation

APPLIED SOFT COMPUTING 2025年 172卷

作者： Pita, Javier Llerena, Juan P. Patricio, Miguel A. Berlanga, Antonio Usero, Luis Grp MasMovil MasMovil Team Ave Bruselas 38 Madrid 28108 Spain Univ Alcala Cognit Sci Res Grp Ctra Madrid Barcelona km Campus UnivCtra Madrid Barcelona km33600 Madrid 28805 Spain Univ Carlos III Madrid Comp Sci & Engn Dept Appl Artificial Intelligence Grp Avda Gregorio Peces-Barba & Martinez22Colmenarej Madrid 28270 Spain

This paper presents Video object segmentation Enhanced with Segment Anything Model (VOS-E-SAM), a multistage architecture for Semi-supervised Video object segmentation (SVOS) using the foundational Segment Anything Model (SAM) architecture, aimed at addressing the challenges of mask degradation over time in long video sequences. Our architectural approach enhances the object masks produced by the XMem model by incorporating SAM. This integration uses various input combinations and low-level computer vision techniques to generate point prompts, in order to improve mask continuity and accuracy throughout the entire video cycle. The main challenge addressed is the fading or vanishing of object masks in long video sequences due to problems such as changes in object appearance, occlusions, camera movements, and approach changes. Both the baseline architecture and the newer high-quality version are tested, addressing the primary challenge of object mask fading or vanishing in long video sequences due to changes in object appearance, occlusions, camera movements, and variations in approach. Through rigorous experimentation with different prompt configurations, we identified an outstanding configuration of SAM inputs to improve mask refinement. Evaluations on benchmark long video datasets, such as LongDataset and LVOS, show that our approach significantly improves mask quality in single-object extended video sequences proven by percentage increments on jaccard index (J ) and contour accuracy (F) based metrics (mean, recall and decay). Our results show remarkable improvements in mask persistence and accuracy, which sets a new standard for the integration of foundational models in video segmentation and lays the foundation for future research in this field. ***-E-SAM

关键词： Video object segmentation Foundation model object segmentation Long-term videos Deep learning

来源：评论

学校读者我要写书评

暂无评论

CoNet: A Consistency-Oriented Network for Camouflaged object segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第1期35卷 287-299页

作者： Wu, Fei Yin, Jun Li, Xiaochuan Wu, Jianfeng Jin, Da Yang, Jiamin Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310058 Peoples R China Zhejiang Univ Polytech Inst Zhejiang Hangzhou 310058 Peoples R China Dahua Technol Co Ltd Hangzhou 310053 Peoples R China Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310058 Peoples R China

Camouflaged object segmentation (COS) is a recently emerging task due to its broad application prospect. The coloration and texture similarities between the objects and their surroundings makes it a challenging task. Motivated by this, we propose a consistency-oriented network (CoNet) to address these challenges by looking into the visual consistencies between object and background. Specifically, we design a primary detection module (PDM) to firstly locate the object by fusing the backbone features. A filter is introduced to better focus on the object's foreground feature based on its primary location. To obtain the visual consistency between the object and background, the foreground feature is then fed into the consistency evaluation module (CEM) to interact with the global feature. Both features are simultaneously processed by a shared discriminator and then fused together to attain the consistency attention map. The final feature refinement is conducted in the detail refinement module (DRM) by merging the consistency attention map with the global features via hierarchical feature fusion. Extensive experiments on benchmark COS datasets show that the proposed CoNet outperforms the state-of-the-art (SOTA) models in most cases. Ablation experiments verify the effectiveness of different backbones, designed modules and upsampling methods. Furthermore, extra studies on the labelling techniques and interdisciplinary applications demonstrate the great potential of the proposed CoNet.

关键词： Feature extraction Visualization object segmentation object detection Estimation object recognition Image resolution Camouflaged object detection camouflaged object segmentation consistency-oriented global-foreground consistency

来源：评论

学校读者我要写书评

暂无评论

StreamMOS: Streaming Moving object segmentation With Multi-View Perception and Dual-Span Memory

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第2期10卷 1146-1153页

作者： Li, Zhiheng Cui, Yubo Zhong, Jiexi Fang, Zheng Northeastern Univ Fac Robot Sci & Engn Shenyang 110819 Peoples R China Northeastern Univ Natl Frontiers Sci Ctr Ind Intelligence & Syst Opt Shenyang 110819 Peoples R China Northeastern Univ Key Lab Data Analyt & Optimizat Smart Ind Minist Educ Shenyang 110819 Peoples R China

Moving object segmentation based on LiDAR is a crucial and challenging task for autonomous driving and mobile robotics. Most approaches explore spatio-temporal information from LiDAR sequences to predict moving objects in the current frame. However, they often focus on transferring temporal cues in a single inference and regard every prediction as independent of others. This may lead to inconsistent segmentation results for the same object across different frames. To solve this issue, we propose a streaming network with a memory mechanism, called StreamMOS, to build the association of features and predictions among multiple inferences. Specifically, we utilize a short-term memory to convey historical features, which can be regarded as spatial priors of moving objects and are used to enhance current inference by temporal fusion. Meanwhile, we build a long-term memory to store previous predictions and exploit them to refine current forecasts at the voxel and instance levels through voting. Besides, we apply multi-view encoder with cascaded projection and asymmetric convolution to extract motion feature of objects in different representations. Extensive experiments validate that our algorithm gets competitive performance on SemanticKITTI and Sipailou Campus datasets.

关键词： Laser radar Three-dimensional displays Motion segmentation Feature extraction Point cloud compression object segmentation Heuristic algorithms Convolution Dynamics Decoding Computer vision for transportation deep learning methods semantic scene understanding

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware focal loss for object segmentation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 149卷

作者： Chen, Lei Wang, Yang Yang, Jibin Zheng, Yunfei Han, Tong Zhang, Bo Cao, Tieyong Army Engn Univ PLA Nanjing 210007 Peoples R China PLA Army Acad Artillery & Air Def Hefei 230031 Peoples R China Natl Def Univ Sci & Technol Inst Int Relat Nanjing 210012 Peoples R China

In the loss function of object segmentation models, misclassified pixels whose prediction are opposite to the ground truth and uncertain pixels whose predicted probability is close to 0.5 are more important for model training. Focusing on misclassified pixels can improve the segmentation accuracy of the model, and focusing on uncertain pixels can help the model to form better decision surfaces. However, existing methods fail to take both types of pixels into account simultaneously. To enhance the learning on these two types of important pixels, the Uncertainty-aware Focal Loss (UFL) is proposed based on the analysis of Uncertainty-aware Loss (UAL). Then, by leveraging the S-shaped property of the sigmoid function, a loss function is constructed that can simultaneously increase the loss and loss derivatives of misclassified and uncertain pixels. In order to solve the gradient vanishing problem of the sigmoid function on well-classified pixels, a regularization constraint term is defined, whose value is the square of predicted probability. Finally, the pixel loss value is dynamically adjusted at different stages of training according to the changes in the contributions of misclassified and uncertain pixels to the model training, which improves the targeted learning for misclassified and uncertain pixels. Experimental results on two different types of network structures and six datasets demonstrate that the proposed method can better segment the uncertain and misclassified pixels. Especially, on the DUT-O dataset, UFL improves mean Intersection over Union (mIoU) by almost 2.7 % compared to UAL.

关键词： Loss function object segmentation Misclassified pixel Uncertain pixel

来源：评论

学校读者我要写书评

暂无评论

MoBox: Enhancing Video object segmentation With Motion-Augmented Box Supervision

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第1期35卷 405-417页

作者： Li, Xiaomin Wang, Qinghe Li, Dezhuang Ge, Mengmeng Jia, Xu He, You Lu, Huchuan Dalian Univ Technol Sch Artificial Intelligence Dalian 116024 Peoples R China Dalian Univ Technol Sch Informat & Commun Engn Dalian 116024 Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China

We propose MoBox, a low-cost solution for semi-supervised video object segmentation that requires only bounding boxes as manual annotations for training. Built upon a mature semi-supervised video object segmentation network, we redesign the training losses and employ a more stringent training strategy. Specifically, we introduce a well-designed constraint term that enhances traditional spatial projection by simultaneously leveraging the projections of both the ground-truth box and the predicted mask across two axes, rather than evaluating discrepancies along the x-axis and y-axis independently. To harness the intrinsic properties of videos, considering the underlying correspondence between motion represented by optical flow and the original image, we incorporate motion coherence information into the color consistency loss as supplementary information and propose a motion discrepancy loss to obtain accurate boundaries. Additionally, to mitigate the ambiguity of weak supervision, we further introduce the pseudo strict constraint during training, which significantly improves model performance. Our approach yields competitive scores on popular benchmarks, achieving a J & F score of 78.6 on the DAVIS 2017 validation set and an Overall score of 78.0 on the YouTube-VOS 2018 validation set. These results highlight the efficacy of MoBox, demonstrating that the semi-supervised video object segmentation model can be effectively trained using only motion-augmented box supervision and intrinsic information of videos.

关键词： Annotations Training Optical flow Task analysis object segmentation Image color analysis Circuits and systems Video object segmentation box annotations motion constraint optical flow

来源：评论

学校读者我要写书评

暂无评论

Scribble-Supervised Video object segmentation via Scribble Enhancement

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第4期35卷 2999-3012页

作者： Gao, Xingyu Li, Zuolei Shi, Hailong Chen, Zhenyu Zhao, Peilin Chinese Acad Sci Inst Microelect Beijing 100029 Peoples R China State Grid Corp China Big Data Ctr Beijing 100031 Peoples R China China Elect Power Res Inst Beijing 100192 Peoples R China Tencent AI Lab Shenzhen 518000 Peoples R China

Current video object segmentation methods heavily rely on pixel-level mask annotations when training, which are expensive and time-consuming to acquire. To address this problem, some approaches try to train with sparse scribble annotations and take sparse target scribble as initial information for inference. However, due to the sparsity of scribble annotations, the performance is often limited, and the corresponding loss function needs to be designed. Inspired by the powerful ability of Segment Anything Model (SAM) to leverage prompt for segmentation, we argue that this problem can be alleviated by improving the quality of scribble. Therefore, we propose SEVOS, a framework for scribble-supervised video object segmentation, which contains a scribble enhancement algorithm and an semi-supervised video object segmentation network. Specifically, the scribble enhancement algorithm first samples corresponding positive sample points and negative sample points from target scribbles, and then feeds them into the SAM in turn, achieving high-quality scribble enhancement without human intervention. This algorithm augments the scribble-annotated video dataset, which is used for additional training of the model. Furthermore, we design a post-processing enhancement algorithm to further improve the prediction results. The obtained model outperforms state-of-the-art methods with a considerable performance gap, indicating the generalization and effectiveness of the proposed model.

关键词： Annotations Training object segmentation Prediction algorithms Circuits and systems Reliability Accuracy Costs Transformers Target tracking Video object segmentation weakly supervised segment anything scribble enhancement

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Referring Video object segmentation With object-Centric Pseudo-Guidance

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 1320-1333页

作者： Wang, Weikang Su, Yuting Liu, Jing Sun, Wei Zhai, Guangtao Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ AI Inst Inst Image Commun & Network Engn MoE Key Lab Artificial Intelligence Shanghai 200240 Peoples R China

Referring video object segmentation (RVOS) is an emerging task for multimodal video comprehension while the expensive annotating process of object masks restricts the scalability and diversity of RVOS datasets. To relax the dependency on expensive mask annotations and take advantage from large-scale partially annotated data, in this paper, we explore a novel extended RVOS task, namely weakly supervised referring video object segmentation (WRVOS), which employs multiple weak supervision sources, including object points and bounding boxes. Correspondingly, we propose a unified WRVOS framework. Specifically, an object-centric pseudo mask generation method is introduced to provide effective shape priors for the pseudo guidance of spatial object location. Then, a pseudo-guided optimization strategy is proposed to effectively optimize the object outlines in terms of spatial location and projection density with a multi-stage online learning strategy. Furthermore, a multimodal cross-frame level set evolution method is proposed to iteratively refine the object boundaries considering both temporal consistency and cross-modal interactions. Extensive experiments are conducted on four publicly available RVOS datasets, including A2D Sentences, J-HMDB Sentences, Ref-DAVIS, and Ref-YoutubeVOS. Performance comparison shows that the proposed method achieves state-of-the-art performance in both point-supervised and box-supervised settings.

关键词： Shape object segmentation Weak supervision Semantics Level set Transformers Annotations Feature extraction Supervised learning Optimization Referring video object segmentation weakly supervised segmentation pseudo-guided learning level set evolution

来源：评论

学校读者我要写书评

暂无评论

Efficient Moving object segmentation in LiDAR Point Clouds Using Minimal Number of Sweeps

IEEE OPEN JOURNAL OF SIGNAL PROCESSING

引用

IEEE OPEN JOURNAL OF SIGNAL PROCESSING 2025年 6卷 118-128页

作者： Rozsa, Zoltan Madaras, Akos Sziranyi, Tamas HUN REN Inst Comp Sci & Control HUN REN SZTAK Machine Percept Res Lab H-1111 Budapest Hungary Budapest Univ Technol & Econ Fac Transportat Engn & Vehicle Engn Dept Mat Handling & Logist Syst H-1111 Budapest Hungary

LiDAR point clouds are a rich source of information for autonomous vehicles and ADAS systems. However, they can be challenging to segment for moving objects as - among other things - finding correspondences between sparse point clouds of consecutive frames is difficult. Traditional methods rely on a (global or local) map of the environment, which can be demanding to acquire and maintain in real-world conditions and the presence of the moving objects themselves. This paper proposes a novel approach using as minimal sweeps as possible to decrease the computational burden and achieve mapless moving object segmentation (MOS) in LiDAR point clouds. Our approach is based on a multimodal learning model with single-modal inference. The model is trained on a dataset of LiDAR point clouds and related camera images. The model learns to associate features from the two modalities, allowing it to predict dynamic objects even in the absence of a map and the camera modality. We propose semantic information usage for multi-frame instance segmentation in order to enhance performance measures. We evaluate our approach to the SemanticKITTI and Apollo real-world autonomous driving datasets. Our results show that our approach can achieve state-of-the-art performance on moving object segmentation and utilize only a few (even one) LiDAR frames.

关键词： Laser radar Point cloud compression object segmentation Cameras Autonomous vehicles Training Proposals Knowledge transfer Vehicle dynamics Semantics LiDAR point clouds moving object segmentation knowledge transfer autonomous driving

来源：评论

学校读者我要写书评

暂无评论

A dynamic dropout self-distillation method for object segmentation

引用

COMPLEX & INTELLIGENT SYSTEMS 2025年第1期11卷 1-14页

作者： Chen, Lei Cao, Tieyong Zheng, Yunfei Wang, Yang Zhang, Bo Yang, Jibin Army Engn Univ PLA Nanjing 210007 Peoples R China PLA Army Acad Artillery & Air Def Hefei 230031 Peoples R China Natl Def Univ Sci & Technol Inst Int Relat Nanjing 210012 Peoples R China

There is a phenomenon that better teachers cannot teach out better students in knowledge distillation due to the capacity mismatch. Especially in pixel-level object segmentation, there are some challenging pixels that are difficult for the student model to learn. Even if the student model learns from the teacher model for each pixel, the student's performance still struggles to show significant improvement. Mimicking the learning process of human beings from easy to difficult, a dynamic dropout self-distillation method for object segmentation is proposed, which solves this problem by discarding the knowledge that the student struggles to learn. Firstly, the pixels where there is a significant difference between the teacher and student models are found according to the predicted probabilities. And these pixels are defined as difficult-to-learn pixel for the student model. Secondly, a dynamic dropout strategy is proposed to match the capability variation of the student model, which is used to discard the pixels with hard knowledge for the student model. Finally, to validate the effectiveness of the proposed method, a simple student model for object segmentation and a virtual teacher model with perfect segmentation accuracy are constructed. Experiment results on four public datasets demonstrate that, when there is a large performance gap between the teacher and student models, the proposed self-distillation method is more effective in improving the performance of the student model compared to other methods.

关键词： Self-distillation object segmentation Dynamic dropout Capacity mismatch

来源：评论

学校读者我要写书评

暂无评论

object segmentation Based on Pseudo Supervision Relearning Under Extremely Weak Annotations for Remote Sensing Images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Liu, Yanan Zhu, Wanning Zhang, Libao Beijing Normal Univ Sch Artificial Intelligence Beijing 100875 Peoples R China

Weakly annotated object segmentation for remote sensing images (RSIs) has attracted lots of attention due to its low labeling costs. However, annotating a huge amount of multiclass RSIs with image labels is still highly dependent on specific expert knowledge and, thus, requires considerable labeling costs. In this article, intending to further alleviate the labor-intensive labeling costs, we introduce a novel extremely weak annotation condition. In this condition, a substantial portion of samples are unlabeled, while merely a small number of samples are labeled with inexact image-level annotations. To achieve object segmentation under extremely weak annotations, we propose pseudo supervision relearning (PSRL), a novel three-stage framework with the core insight of effectively harnessing the potentially valuable supervision clues stored in abundant unlabeled data. In the first stage, the extremely weak annotations are switched to fine-grained but noisy pseudo supervision with the aid of image-level semantic learning and attention-guided data augmentation. Then, a category-aware dataset resplit strategy based on the masking perturbation mechanism is designed, aiming at adaptively selecting high-quality pixelwise pseudomasks from the artificially generated pseudo supervision and achieving class-balanced reliable-unreliable labels division. Ultimately, we devise a novel dynamic thresholding strategy (DTS)-guided relearning network to take full advantage of the valuable semantic information in the resplit dataset. Experimental results on two public RSI datasets show the effectiveness of the proposed framework. Utilizing less supervised information, the proposed method yields competing results compared to weakly supervised learning-based methods with complete image-level annotations.

关键词： Annotations object segmentation Semantics Labeling Training Remote sensing Costs Perturbation methods Reliability engineering Data models object detection pseudo supervision relearning (PSRL) remote sensing image (RSI) processing semantic segmentation weakly supervised 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：