检索结果-内蒙古大学图书馆

weakly supervised semantic segmentation via saliency perception with uncertainty-guided noise suppression

VISUAL COMPUTER 2025年第4期41卷 2891-2906页

作者： Liu, Xinyi Huang, Guoheng Yuan, Xiaochen Zheng, Zewen Zhong, Guo Chen, Xuhang Pun, Chi-Man Guangdong Univ Technol Guangzhou Peoples R China Macao Polytech Univ Macau Peoples R China Guangdong Univ Foreign Studies Guangzhou Peoples R China Huizhou Univ Huizhou Peoples R China Univ Macau Macau Peoples R China

weakly supervised semantic segmentation (WSSS) has become increasingly popular for achieving remarkable segmentation with only image-level labels. Current WSSS approaches extract Class Activation Mapping (CAM) from classification models to produce pseudo-masks for segmentation supervision. However, due to the gap between image-level supervised classification loss and pixel-level CAM generation tasks, the model tends to activate discriminative regions at the image level rather than pursuing pixel-level classification results. Moreover, insufficient supervision leads to unrestricted attention diffusion in the model, further introducing inter-class recognition noise. In this paper, we introduce a framework that employs Saliency Perception and Uncertainty, which includes a Saliency Perception Module (SPM) with Pixel-wise Transfer Loss (SP-PT), and an Uncertainty-guided Noise Suppression method. Specifically, within the SPM, we employ a hybrid attention mechanism to expand the receptive field of the module and enhance its ability to perceive salient object features. Meanwhile, a Pixel-wise Transfer Loss is designed to guide the attention diffusion of the classification model to non-discriminative regions at the pixel-level, thereby mitigating the bias of the model. To further enhance the robustness of CAM for obtaining more accurate pseudo-masks, we propose a noise suppression method based on uncertainty estimation, which applies a confidence matrix to the loss function to suppress the propagation of erroneous information and correct it, thus making the model more robust to noise. We conducted experiments on the PASCAL VOC 2012 and MS COCO 2014, and the experimental results demonstrate the effectiveness of our proposed framework. Code is available at https://***/pur-suit/SPU.

关键词： weakly supervised semantic segmentation Class Activation Mapping Uncertainty estimation Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

weakly supervised semantic segmentation for ancient architecture based on multiscale adaptive fusion and spectral clustering

引用

COMPUTERS & GRAPHICS-UK 2025年 126卷

作者： Sun, Ruifei Zhang, Sulan Su, Meihong Hu, Lihua Zhang, Jifu Taiyuan Univ Sci & Technol Sch Comp Sci & Technol Taiyuan 030024 Peoples R China

Existing methods of weakly supervised semantic segmentation for ancient architecture have several limitations including difficulty in capturing decorative details and achieving precise segmentation boundaries due to the many details and complex shapes of these structures. To mitigate the effect of the above issues in ancient architecture images, this paper proposes a method for weakly supervised semantic segmentation of ancient architecture based on multiscale adaptive fusion and spectral clustering. Specifically, low-level features are able to capture localized details in an image, which helps to identify small objects. In contrast, highlevel features can capture the overall shape of an object, making them more effective in recognizing large objects. We use a gating mechanism to adaptively fuse high-level and low-level features in order to retain objects of different sizes. Additionally, by employing spectral clustering, pixels in ancient architectural images can be divided into different regions based on their feature similarities. These regions serve as processing units, providing precise boundaries for class activation map (CAM) and improving segmentation accuracy. Experimental results on the Ancient Architecture, Baroque Architecture, MS COCO 2014 and PASCAL VOC 2012 datasets show that the method outperforms the existing weakly supervised methods, achieving 46.9%, 55.8%, 69.9% and 38.3% in Mean Intersection Over Union (MIOU), respectively. The code is available at https://***/hao530/***

关键词： weakly supervised semantic segmentation Ancient architecture Multiscale Adaptive fusion Spectral clustering

来源：评论

学校读者我要写书评

暂无评论

M-SEE: A multi-scale encoder enhancement framework for end-to-end weakly supervised semantic segmentation

引用

PATTERN RECOGNITION 2025年 162卷

作者： Yang, Ziqian Zhao, Xinqiao Yao, Chao Zhang, Quan Xiao, Jimin Xian Jiaotong Liverpool Univ Suzhou Peoples R China UNIV LIVERPOOL LIVERPOOL England Univ Sci & Technol Beijing Beijing Peoples R China

End-to-end image-level weakly supervised semantic segmentation (WSSS) has received increasing attention due to its simple but effective implementation. It helps to alleviate the laborious annotation costs required in semantic segmentation. In this work, we find that not all discriminative features can be extracted by a transformer encoder under image-level supervision. Thus, the decoder in end-to-end WSSS fails to predict a satisfying segmentation result. To solve this issue, we propose a Multi-Scale Encoder Enhancement (M- SEE) framework for enabling the encoder to extract comprehensive discriminative features and improve WSSS performance. Specifically, we first resize the original training image to various scales and calculate Class Activation Map (CAM) for each scale image. Then, reliable discriminative regions are mined based on the CAM and decoder segmentation result. Finally, a knowledge distillation loss is calculated among features of original scale and the scaled features of selected reliable discriminative regions. Experimental results show that our M-SEE framework achieves new state-of-the-art performances with 74.8% on PASCAL VOC 2012 test split and 45.8% on MS COCO 2014 validation split. Codes will be released.

关键词： weakly supervised semantic segmentation End-to-end framework Knowledge distillation Image-level labels

来源：评论

学校读者我要写书评

暂无评论

Class activation map guided level sets for weakly supervised semantic segmentation

引用

PATTERN RECOGNITION 2025年 165卷

作者： Wang, Yifan Schaefer, Gerald Liu, Xiyao Dong, Jing Jing, Linglin Wei, Ye Xie, Xianghua Fang, Hui Loughborough Univ Dept Comp Sci Loughborough England Cent South Univ Sch Comp Sci & Engn Changsha Peoples R China Dalian Univ Key Lab Adv Design & Intelligent Comp Dalian Peoples R China Swansea Univ Dept Comp Sci Swansea Wales

weakly supervised semantic segmentation (WSSS) aims to achieve pixel-level fine-grained image segmentation using only weak guidance such as image-level class labels, thus significantly decreasing annotation costs. Despite the impressive performance showcased by current state-of-the-art WSSS approaches, the lack of precise object localisation limits their segmentation accuracy, especially for pixels close to object boundaries. To address this issue, we propose a novel class activation map (CAM)-based level set method to effectively improve the quality of pseudo-labels by exploring the capability of level sets to enhance the segmentation accuracy at object boundaries. To speed up the level set evolution process, we use Fourier neural operators to simulate the dynamic evolution of our level set method. Extensive experimental results show that our approach significantly outperforms existing WSSS methods on both PASCAL VOC 2012 and MS COCO datasets.

关键词： weakly supervised semantic segmentation Class activation map Pseudo-label Level set Fourier neural operator

来源：评论

学校读者我要写书评

暂无评论

FL-W3S: Cross-domain federated learning for weakly supervised semantic segmentation of white blood cells

引用

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS 2025年 195卷 105806-105806页

作者： Madni, Hussain Ahmad Umer, Rao Muhammad Zottin, Silvia Marr, Carsten Foresti, Gian Luca Univ Udine Dept Comp Sci & Artificial Intelligence I-33100 Udine Italy Helmholtz Zentrum Munchen Inst AI Hlth D-85764 Munich Germany

Background: segmentation models for clinical data experience severe performance degradation when trained on a single client from one domain and distributed to other clients from different domain. Federated Learning (FL) provides a solution by enabling multi-party collaborative learning without compromising the confidentiality of clients' private data. Methods: In this paper, we propose a cross-domain FL method for weakly supervised semantic segmentation (FL-W3S) of white blood cells in microscopic images. We perform model training on multiple clients with different data distributions to obtain a global aggregated model using only image-level class labels for semantic segmentation of white blood cells. A multi-class token transformer model learns the relationship between patch tokens and class tokens during collaborative learning and generates class-specific localization maps for mask predictions. To rectify the localization maps, we use patch-level pairwise affinity obtained from patch-to-patch transformer attention. Results: We evaluate performance of the proposed semantic segmentation method on two different datasets of white blood cells from different domains. Our experimental results show that for two datasets, there is 2.56% and 1.39% increase in performance of the proposed method over existing state-of-the-art methods. Conclusion: The combination of federated learning for collaborative model training while preserving data privacy, alongside white blood cell segmentation techniques for precise cell identification, enhances diagnostic accuracy and personalized treatment strategies in clinical applications, particularly in hematology and pathology. More specifically, it involves isolating white blood cell from blood smear for further analysis such as automated blood cell counting, morphological analysis, cell classification, disease diagnosis and monitoring.

关键词： Federated learning White blood cell weakly supervised semantic segmentation Transformer attention

来源：评论

学校读者我要写书评

暂无评论

Contrastive activation maps with superpixel rectification for weakly supervised semantic segmentation: When superpixels meet CAMs ☆

引用

DIGITAL SIGNAL PROCESSING 2025年 162卷

作者： Shi, Huilin Liu, Yukun Wang, Shaofan Sun, Yanfeng Yin, Baocai Beijing Univ Technol Sch Informat Sci & Technol Beijing Key Lab Multimedia & Intelligent Software Beijing 100124 Peoples R China

The weakly supervised semantic segmentation (WSSS) task amounts to segmenting all pixels by using weaker annotations instead of pixel-level ones. It suffers from two ubiquitous issues: over-activation and under-activation, incurred from unsatisfactory class activation maps (CAMs). Existing methods cannot balance this dilemma due to two reasons. (a) Most of methods learn less discriminative parts iteratively, leading to discontinuous parts of activation regions. (b) Most of methods refine CAMs by learning inter-pixel affinity from a global perspective which takes high complexity. We propose Contrastive Activation Maps with Superpixel Rectification (SRCAM) for WSSS by incorporating two effective tools: superpixel segmentation and contrastive learning with CAMs together. Typically, superpixels rectify those incomplete vanilla CAMs by examining each activation region based on its proportion with respect to each superpixel. After learning CAMs, SRCAM disentangles foreground objects and background from local patches by learning a cross-patch foreground-background contrast, and then preserves the invariance of activation maps from patch level to image level by learning a local-to-global activation map contrast. Experiments show that SRCAM achieves the state-of-the-art performance (72.8% mIoU) on the PASCAL VOC 2012 among 54 WSSS methods, and achieves the top-1 performance (44.8% mIoU) on the MS COCO 2014 among 27 WSSS methods. Code is available at https://***/wangsfan/SRCAM.

关键词： weakly supervised semantic segmentation Activation map Contrastive learning Superpixel segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-representation fusion learning for weakly supervised semantic segmentation

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 277卷

作者： Li, Yongqiang Hu, Chuanping Ren, Kai Xi, Hao Fan, Jinhao Zhengzhou Univ Sch Elect & Informat Engn Zhengzhou Peoples R China Zhengzhou Univ Sch Cyber Sci & Engn Zhengzhou Peoples R China Zhengzhou Univ Publ Secur Res Inst Zhengzhou Peoples R China

weakly supervised semantic segmentation (WSSS) with image-level labels offers a promising solution to the expensive problem of pixel-level annotation. However, the prevalent use of Class Activation Maps (CAMs), while effective, often results in inaccurate object boundaries and poor edge details in generated pseudo- labels. To overcome these limitations, this paper presents a novel Multi-representation Fusion Learning (MFL) framework that leverages the remarkable capabilities of the Segment Anything Model (SAM) to enhance feature learning in WSSS. The MFL framework directly addresses the shortcomings of CAM-based pseudo-labels by incorporating rich semantic and edge information extracted from SAM. This is achieved through two dedicated modules: the semantic-Guided Distilled Attention (SGDA) module and the Edge-Guided Distilled Attention (EGDA) module. These modules enable the network to learn more discriminative features by leveraging the SAM's knowledge, leading to higher-quality pseudo-labels. Furthermore, the proposed Multi-representation Fusion Module (MFM), based on a dual-layer routing attention mechanism, effectively fuses the semantic and edge features learned by the SGDA and EGDA, resulting in more refined pseudo-labels for training. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets demonstrate that the MFL framework significantly outperforms existing WSSS methods, achieving state-of-the-art performance.

关键词： weakly supervised semantic segmentation Segment anything model Multi-representation Attention module Fusion learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing multi-task network with learned prototypes for weakly supervised semantic segmentation

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2025年 134卷

作者： Zhou, Lei Wang, Jiasong Luo, Jing Guo, Yuheng Li, Xiaoxiao Univ Shanghai Sci & Technol Shanghai Peoples R China Shanghai Waigaoqiao Shipbuilding & Offshore Co Ltd Shanghai Peoples R China Shanghai Inst Technol Shanghai Peoples R China

weakly supervised semantic segmentation (WSSS) presents a challenging task wherein semantic objects are extracted solely through the utilization of image-level labels as supervision. One common category of stateof-the-art solutions depends on the generation of pseudo pixel-level annotations via the use of localization maps. Nevertheless, in the majority of such solutions, the quality of pseudo annotations may not effectively fulfill the requirements of semantic segmentation owing to the incomplete nature of the localization maps. In order to generate denser localization maps for WSSS, this paper proposes the use of a prototype learning guided multi-task network. Initially, the prototypes (also referred to as prototypical feature vectors) are employed to depict the similarities between images. Specifically, the shared information among different training images is thoroughly exploited to concomitantly learn the prototypes for both foreground categories and background. This approach facilitates the localization of more reliable background pixels and foreground regions by evaluating the similarities between the representative prototypes and the extracted features of pixels. Additionally, the learned prototypes can be incorporated into the multi-task network to enhance the efficiency of parameter optimization by adaptively rectifying errors in pixel-level supervision. Therefore, the optimization of the multi-task network for object localization and the production of high-quality proxy annotations can be achieved by means of clean image-level labels and refined pixel-level supervision working in conjunction. By selecting and refining proxy annotations, the performance of the segmentation algorithm can be further improved. Extensive experiments conducted on two datasets, namely, PASCAL VOC 2012 and COCO 2014, have substantiated the fact that the prototype learning guided multi-task network being proposed outperforms the current state-of-the-art (SOTA) methods in terms of

关键词： weakly supervised semantic segmentation Multi-task network Prototype learning

来源：评论

学校读者我要写书评

暂无评论

weakly supervised semantic segmentation by a Class-Level Multiple Group Cosegmentation and Foreground Fusion Strategy

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2020年第12期30卷 4823-4836页

作者： Meng, Fanman Luo, Kunming Li, Hongliang Wu, Qingbo Xu, Xiaolong Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

weakly supervised semantic segmentation uses image-level labels to extract object regions. The existing methods focus on efficiently training CNN-based segmentation networks using the image-level labels. In contrast to the existing methods, this paper proposes a new fusion-based method, which first segments the foregrounds of each image by multiple group cosegmentation and then generates the semantic segmentation by combining the foregrounds. Specifically, a new CNN-based multiple group cosegmentation network is first proposed to segment foregrounds employing two cues, the discriminative cue and the local-to-global cue. Then, the fusion method is proposed to simply perform semantic segmentation based on the multiple group cosegmentation results. Experiments on the PASCAL VOC 2012 and MS COCO 2017 datasets demonstrate the effectiveness of the proposed method with mIoU values that are obviously larger than those of the existing methods.

关键词： Image segmentation semantics Task analysis Training Videos Convolutional neural networks Integrated circuit modeling Multiple group cosegmentation weakly supervised semantic segmentation class activation map region fusion

来源：评论

学校读者我要写书评

暂无评论

weakly supervised semantic segmentation by knowledge graph inference

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 138卷

作者： Zhang, Jia Peng, Bo Wu, Xi Hu, Jie Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 610031 Sichuan Peoples R China Chengdu Univ Informat Technol Sch Comp Sci Chengdu Peoples R China

The weakly supervised semantic segmentation (WSSS) training based on image-level labels in convolutional neural network (CNN) is usually divided into two stages: multi-label classification and semantic segmentation. However, most of the existing work focuses on the improvement of the multi-label classification network stage, and little effort has been done to improve the performance of the downstream segmentation networks. In addition, CNN-based local convolution lacks in modeling extensive dependencies among categories. Therefore, in this paper, we propose a graph reasoning method to improve both the upstream and the downstream stages of the multi-label classification network and the semantic segmentation networks. In the multi-label classification network, we utilize external knowledge combined with a graph convolutional network (GCN) to perform global reasoning on the dependencies of each category. In the segmentation network, the Graph Reasoning Mapping Module (GRM) is proposed to explore the knowledge acquired from text corpora and facilitate contextual reasoning in various categories of image regions. The proposed GRM module is able to enhance the feature representation of local convolutions on the high-level semantics of the segmentation network, and adaptively learn the semantic consistency of each sample. We achieve state-of-the-art WSSS performance on PASCAL VOC 2012 and MS-COCO 2014 datasets with only image-level supervision. Extensive experiments on multi-label classification networks and semantic segmentation networks demonstrate the effectiveness of our proposed graph reasoning method on WSSS. Our code is available at:https://***/ JIA-ZHANG666/GRM_layer.

关键词： weakly supervised semantic segmentation Convolutional neural networks Graph convolutional network External knowledge Graph reasoning

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：