检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

62 篇 期刊文献
32 篇 会议

馆藏范围

94 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

91 篇 工学
- 65 篇 计算机科学与技术...
- 43 篇 电气工程
- 16 篇 软件工程
- 12 篇 测绘科学与技术
- 9 篇 信息与通信工程
- 6 篇 控制科学与工程
- 5 篇 电子科学与技术（可...
- 3 篇 环境科学与工程（可...
- 2 篇 机械工程
- 2 篇 生物医学工程（可授...
- 1 篇 光学工程
- 1 篇 动力工程及工程热...
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 石油与天然气工程
- 1 篇 交通运输工程
29 篇 医学
- 23 篇 临床医学
- 5 篇 基础医学(可授医学...
- 4 篇 特种医学
15 篇 理学
- 9 篇 地球物理学
- 3 篇 物理学
- 3 篇 地理学
- 2 篇 数学
- 2 篇 生物学
- 1 篇 统计学（可授理学、...
3 篇 管理学
- 2 篇 管理科学与工程(可...
- 1 篇 公共管理

主题

94 篇 weakly supervise...
16 篇 class activation...
11 篇 semantic segment...
10 篇 deep learning
10 篇 training
9 篇 image segmentati...
9 篇 semantics
5 篇 task analysis
5 篇 attention mechan...
4 篇 image-level labe...
4 篇 weakly supervise...
4 篇 contrastive lear...
3 篇 annotations
3 篇 feature extracti...
2 篇 vision transform...
2 篇 object detection
2 篇 high-resolution ...
2 篇 transformer
2 篇 superpixel
2 篇 magnetic resonan...

机构

3 篇 korea adv inst s...
2 篇 tianjin univ col...
2 篇 beijing normal u...
2 篇 univ elect sci &...
2 篇 xian jiaotong li...
2 篇 south china univ...
2 篇 southwest jiaoto...
1 篇 northeastern uni...
1 篇 dalian univ key ...
1 篇 gachon univ dept...
1 篇 guangdong univ f...
1 篇 huizhou univ hui...
1 篇 huaqiao univ col...
1 篇 shanghai ai lab ...
1 篇 9 deng zhuang so...
1 篇 loughborough uni...
1 篇 yuxi normal univ...
1 篇 univ michigan an...
1 篇 monash univ fac ...
1 篇 univ bonn bonn

作者

3 篇 wu qingbo
3 篇 meng fanman
3 篇 li hongliang
3 篇 yoon kuk-jin
3 篇 zhou lei
2 篇 kweon hyeokjun
2 篇 zhang jiacai
2 篇 huang guoheng
2 篇 shen li
2 篇 li zhilin
2 篇 sohel ferdous
2 篇 yoon sung-hoon
2 篇 xu xiaolong
2 篇 cai wentian
2 篇 gao ying
2 篇 bennamoun mohamm...
2 篇 zhong guo
2 篇 zhang yu
2 篇 xu lian
2 篇 yuan xiaochen

语言

89 篇 英文
5 篇 其他

检索条件"主题词=weakly supervised semantic segmentation"

共 94 条记录，以下是41-50 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Hybrid Suppression and Attention with Online Augmentation for weakly supervised semantic segmentation 11

Hybrid Suppression and Attention with Online Augmentation fo...

引用

11th IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) - Empower of Innovative Consumer Technology

作者： Tseng, Li-An Guo, Jing-Ming Lin, Zi-Han Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei Taiwan

ISBN: (纸本)9798350386851;9798350386844

The primary approach in weakly supervised semantic segmentation involves utilizing a classification network to classify input images, extracting the model's regions of interest with Class Activation Maps (CAM), and creating pseudo masks for training the segmentation network. However, the model may excessively focus on certain features and struggle with accurately segmenting object boundaries. We proposed a method to address these issues and experimental results demonstrate our method achieving a pseudo mask mIoU of 71.153 on the PASCAL VOC 2012 training set. By training the semantic segmentation network using these pseudo masks, it achieves mIoU scores of 72.46 and 72.81 on the PASCAL VOC 2012 validation and test sets, superior to the state-of-the-art methods.

关键词： weakly supervised semantic segmentation class activation map deep learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial Erasing Framework via Triplet with Gated Pyramid Pooling Layer for weakly supervised semantic segmentation 1

引用

17th European Conference on Computer Vision (ECCV)

作者： Yoon, Sung-Hoon Kweon, Hyeokjun Cho, Jegyeong Kim, Shinjeong Yoon, Kuk-Jin Korea Adv Inst Sci & Technol Daejeon South Korea

ISBN: (数字)9783031198182

ISBN: (纸本)9783031198175;9783031198182

weakly supervised semantic segmentation (WSSS) has employed Class Activation Maps (CAMs) to localize the objects. However, the CAMs typically do not fit along the object boundaries and highlight only the most-discriminative regions. To resolve the problems, we propose a Gated Pyramid Pooling (GPP) layer which is a substitute for a Global Average Pooling (GAP) layer, and an Adversarial Erasing Framework via Triplet (AEFT). In the GPP layer, a feature pyramid is obtained by pooling the CAMs at multiple spatial resolutions, and then be aggregated into an attention for class prediction by gated convolution. With the process, CAMs are trained not only to capture the global context but also to preserve fine-details from the image. Meanwhile, the AEFT targets an over-expansion, a chronic problem of Adversarial Erasing (AE). Although AE methods expand CAMs by erasing the discriminative regions, they usually suffer from the over-expansion due to an absence of guidelines on when to stop erasing. We experimentally verify that the over-expansion is due to rigid classification, and metric learning can be a flexible remedy for it. AEFT is devised to learn the concept of erasing with the triplet loss between the input image, erased image, and negatively sampled image. With the GPP and AEFT, we achieve new state-of-the-art both on the PASCAL VOC 2012 val/test and MS-COCO 2014 val set by 70.9%/71.7% and 44.8% in mIoU, respectively.

关键词： weakly supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Adversarial Decoupling for weakly supervised semantic segmentation 4th

Adversarial Decoupling for Weakly Supervised Semantic Segmen...

引用

4th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Sun, Guoying Yang, Meng Luo, Wenfeng Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp SYSU Guangzhou Peoples R China

ISBN: (纸本)9783030880132;9783030880125

Image semantic segmentation has been widely used in medical image analysis, autonomous driving and other fields. However, the fully-supervised semantic segmentation network requires a lot of labor cost to label pixel-level training data, so weakly supervised semantic segmentation (WSSS), which requires much easily available supervision, has become a new research hotspot. This paper focuses on tackling the semantic segmentation problem under weak supervision of image-level labels. To estimate more accurate pseudo masks, this paper proposes to jointly explore sub-category clustering, context decoupling augmentation and adversarial climbing to mine more object-related regions. With sub-categories of k-means clustering, model can learn better feature representations, which breaks the dependency of object on the context by decoupling augmentation. The image is perturbed away from the classification boundary to further increase the classification score with adversarial climbing method. In order to verify the effectiveness of the method in this paper, we conduct a large number of experiments on the PASCAL VOC 2012 dataset obtained an excellent performance of 69.8% mIoU on the verification set and 69.5% mIoU on the test set, which surpassed many advanced models of the same level supervision.

关键词： weakly supervised semantic segmentation Context decoupling Adversarial climbing K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A Self-Training Framework Based on Multi-Scale Attention Fusion for weakly supervised semantic segmentation

A Self-Training Framework Based on Multi-Scale Attention Fus...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yang, Guoqing Zhu, Chuang Zhang, Yu Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9781665468916

weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a self-training method that utilizes fused multi-scale class-aware attention maps. Our observation is that attention maps of different scales contain rich complementary information, especially for large and small objects. Therefore, we collect information from attention maps of different scales and obtain multiscale attention maps. We then apply denoising and reactivation strategies to enhance the potential regions and reduce noisy areas. Finally, we use the refined attention maps to retrain the network. Experiments showthat our method enables the model to extract rich semantic information from multi-scale images and achieves 72.4% mIou scores on both the PASCAL VOC 2012 validation and test sets. The code is available at https://***/SMAF.

关键词： weakly supervised semantic segmentation self-training multi-scale attention

来源：评论

学校读者我要写书评

暂无评论

Boat in the Sky: Background Decoupling and Object-aware Pooling for weakly supervised semantic segmentation 22

Boat in the Sky: Background Decoupling and Object-aware Pool...

引用

30th ACM International Conference on Multimedia (MM)

作者： Xu, Jianjun Xie, Hongtao Xu, Hai Wang, Yuxin Liu, Sun-ao Zhang, Yongdong Univ Sci & Technol China Hefei Peoples R China

ISBN: (纸本)9781450392037

Previous image-level weakly-supervised semantic segmentation methods based on Class Activation Map (CAM) have two limitations: 1) focusing on partial discriminative foreground regions and 2) containing undesirable background. The above issues are attributed to the spurious correlations between the object and background (semantic ambiguity) and the insufficient spatial perception ability of the classification network (spatial ambiguity). In this work, we propose a novel self-supervised framework to mitigate the semantic and spatial ambiguity from the perspectives of background bias and object perception. First, a background decoupling mechanism (BDM) is proposed to handle the semantic ambiguity by regularizing the consistency of predicted CAMs from the samples with identical foregrounds but different backgrounds. Thus, a decoupled relationship is constructed to reduce the dependence between the object instance and the scene information. Second, a global object-aware pooling (GOP) is introduced to alleviate spatial ambiguity. The GOP utilizes a learnable object-aware map to dynamically aggregate spatial information and further improve the performance of CAMs. Extensive experiments demonstrate the effectiveness of our method by achieving new state-of-the-art results on both the Pascal VOC 2012 and MS COCO 2014 datasets.

关键词： weakly supervised semantic segmentation weakly supervised learning semantic segmentation background bias

来源：评论

学校读者我要写书评

暂无评论

Class Tokens Infusion for weakly supervised semantic segmentation

Class Tokens Infusion for Weakly Supervised Semantic Segment...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yoon, Sung-Hoon Kwon, Hoyong Kim, Hyeonseong Yoon, Kuk-Jin Korea Adv Inst Sci & Technol Daejeon South Korea

ISBN: (纸本)9798350353013;9798350353006

weakly supervised semantic segmentation (WSSS) relies on Class Activation Maps (CAMs) to extract spatial information from image-level labels. With the success of Vision Transformer (ViT), the migration of ViT is actively conducted in WSSS. This work proposes a novel WSSS framework with Class Token Infusion (CTI). By infusing the class tokens from images, we guide class tokens to possess class-specific distinct characteristics and global-local consistency. For this, we devise two kinds of token infusion: 1) Intra-image Class Token Infusion (I-CTI) and 2) Cross-image Class Token Infusion (C-CTI). In I-CTI, we infuse the class tokens from the same but differently augmented images and thus make CAMs consistent among various deformations (i.e. view, color). In C-CTI, by infusing the class tokens from the other images and imposing the resulting CAMs to be similar, it learns class-specific distinct characteristics. Besides the CTI, we bring the background (BG) concept into ViT with the BG token to reduce the false positive activation of CAMs. We demonstrate the effectiveness of our method on PASCAL VOC 2012 and MS COCO 2014 datasets, achieving state-of-the-art results in weakly supervised semantic segmentation. The code is available at https://***/yoon307/CTI.

关键词： weakly supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

A weakly supervised semantic segmentation Method on Lung Adenocarcinoma Histopathology Images 19th

A Weakly Supervised Semantic Segmentation Method on Lung Ade...

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Lan, Xiaobin Mei, Jiaming Lin, Ruohan Chen, Jiahao Zhang, Yanju Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin Guangxi Peoples R China Huaqiao Univ Coll Comp Sci & Technol Xiamen Peoples R China Huaqiao Univ Xiamen Key Lab CVPR Xiamen Peoples R China

ISBN: (纸本)9789819947416;9789819947423

Accurately distinguishing different tissues is crucial for pathologists to determine the type and degree of lesions. The methods based on class activation maps (CAM) are popular in current research due to their low annotation cost. However, this method has two main drawbacks: (1) as the training deepens, the class activation maps become increasingly concentrated in the most discriminative region and cannot fully cover the object;(2) different tissues may be activated at the same pixel because the binary cross-entropy (BCE) calculates classification loss independently. To alleviate these issues, we propose a new method that combines channel attention (CA) and progressive dropout attention (PDA) to expand the class activation maps and enhance the activation of important features. In addition, after the network converges, we train an additional fully-connected layer and use softmax cross-entropy (SCE) to fine-tune the model parameters and reduce the activation of unrelated tissues. We evaluate our proposed model on the recently released LUAD-HistoSeg dataset. The results illustrate that our model achieved a 76.53% MIoU and outperform the most advanced methods.

关键词： tissue segmentation weakly supervised semantic segmentation attention mechanism class re-activation mapping

来源：评论

学校读者我要写书评

暂无评论

Leveraging Swin Transformer for Local-to-Global weakly supervised semantic segmentation 13

Leveraging Swin Transformer for Local-to-Global Weakly Super...

引用

13th Iranian/3rd International Machine Vision and Image Processing Conference (MVIP)

作者： Ahmadi, Rozhan Kasaei, Shohreh Sharif Univ Technol Dept Comp Engn Tehran Iran

ISBN: (纸本)9798350350494;9798350350500

In recent years, weakly supervised semantic segmentation using image-level labels as supervision has received significant attention in the field of computer vision. Most existing methods have addressed the challenges arising from the lack of spatial information in these labels by focusing on facilitating supervised learning through the generation of pseudolabels from class activation maps (CAMs). Due to the localized pattern detection of Convolutional Neural Networks (CNNs), CAMs often emphasize only the most discriminative parts of an object, making it challenging to accurately distinguish foreground objects from each other and the background. Recent studies have shown that Vision Transformer (ViT) features, due to their global view, are more effective in capturing the scene layout than CNNs. However, the use of hierarchical ViTs has not been extensively explored in this field. This work explores the use of Swin Transformer by proposing "SWTformer" to enhance the accuracy of the initial seed CAMs by bringing local and global views together. SWTformer-V1 generates class probabilities and CAMs using only the patch tokens as features. SWTformer-V2 incorporates a multi-scale feature fusion mechanism to extract additional information and utilizes a background-aware mechanism to generate more accurate localization maps with improved cross-object discrimination. Based on experiments on the PascalVOC 2012 dataset, SWTformer-V1 achieves a 0.98% mAP higher localization accuracy, outperforming state-of-the-art models. It also yields comparable performance by 0.82% mIoU on average higher than other methods in generating initial localization maps, depending only on the classification network. SWTformer-V2 further improves the accuracy of the generated seed CAMs by 5.32% mIoU, further proving the effectiveness of the local-to-global view provided by the Swin transformer. Code available at: https://***/RozhanAhmadi/SWTformer

关键词： weakly supervised semantic segmentation Class Activation Map Hierarchical Vision Transformer Image-level label

来源：评论

学校读者我要写书评

暂无评论

Multiscale Superpixel Affinity for Improved weakly supervised semantic segmentation 36

Multiscale Superpixel Affinity for Improved Weakly Supervise...

引用

36th Chinese Control and Decision Conference (CCDC)

作者： Fu, Yun Wang, Wenwu Zhu, Lei Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan Peoples R China

ISBN: (纸本)9798350387780;9798350387797

weakly supervised semantic segmentation based on image-level labels typically employs strategies of modifying and expanding class activation map(CAM) seeds to achieve semantic segmentation. However, network downsampling can reduce the edge perception of the CAM, leading to problems of under-activation and over-activation, which consequently affect the segmentation quality. To address these issues, this paper proposes a weakly supervised semantic segmentation method based on multi-scale superpixel affinity(MSPA). In this method, a classification network is first used to generate CAMs, which are then refined using a pixel adaptive module to generate pseudo-masks and provide semantic labels for superpixels. Simultaneously, a fully convolutional network is utilized to extract full-size image features, which are mapped onto the superpixel segmentation map to obtain the feature representation of each superpixel. Subsequently, based on the feature representation of superpixels, the affinity between superpixels is calculated. The superpixels associated with foreground and background categories are then clustered separately to generate foreground probability maps and background probability maps to supervise the localisation of the CAMs. Experimental results demonstrate that our method achieves segmentation accuracies of 67.02% and 67.74% on the validation set and test set, respectively, on the Pascal VOC 2012 dataset. This leads to more accurate activation of the CAMs and clearer categories, which significantly outperforms the compared methods in this paper.

关键词： Multi-scale superpixels Fully convolutional network weakly supervised semantic segmentation Class activation map

来源：评论

学校读者我要写书评

暂无评论

Hunting Attributes: Context Prototype-Aware Learning for weakly supervised semantic segmentation

Hunting Attributes: Context Prototype-Aware Learning for Wea...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tang, Feilong Xu, Zhongxing Qu, Zhaojun Feng, Wei Jiang, Xingjian Ge, Zongyuan Monash Univ Fac IT AIM Lab Clayton Vic Australia Monash Univ Fac IT Clayton Vic Australia Cornell Univ Weill Cornell Med Ithaca NY 14853 USA Xian Jiaotong Liverpool Univ Suzhou Peoples R China Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9798350353013;9798350353006

Recent weakly supervised semantic segmentation (WSSS) methods strive to incorporate contextual knowledge to improve the completeness of class activation maps (CAM). In this work, we argue that the knowledge bias between instances and contexts affects the capability of the prototype to sufficiently understand instance semantics. Inspired by prototype learning theory, we propose leveraging prototype awareness to capture diverse and fine-grained feature attributes of instances. The hypothesis is that contextual prototypes might erroneously activate similar and frequently co-occurring object categories due to this knowledge bias. Therefore, we propose to enhance the prototype representation ability by mitigating the bias to better capture spatial coverage in semantic object regions. With this goal, we present a Context Prototype-Aware Learning (CPAL) strategy, which leverages semantic context to enrich instance comprehension. The core of this method is to accurately capture intra-class variations in object features through context-aware prototypes, facilitating the adaptation to the semantic attributes of various instances. We design feature distribution alignment to optimize prototype awareness, aligning instance feature distributions with dense features. In addition, a unified training framework is proposed to combine label-guided classification supervision and prototypes-guided self-supervision. Experimental results on PASCAL VOC 2012 and MS COCO 2014 show that CPAL significantly improves off-the-shelf methods and achieves state-of-the-art performance. The project is available at https://***/Barrett-python/CPAL.

关键词： Attributes semantic segmentation weakly supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共10页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：