检索结果-内蒙古大学图书馆

Local optimization cropping and boundary enhancement for end-to-end weakly-supervised segmentation network

COMPUTER VISION AND IMAGE UNDERSTANDING 2025年 251卷

作者： Wang, Weizheng Zeng, Chao Wang, Haonan Zhou, Lei Changsha Univ Sci & Technol Changsha 410000 Peoples R China

In recent years, the performance of weakly-supervised semantic segmentation(WSSS) has significantly increased. It usually employs image-level labels to generate Class Activation Map (CAM) for producing pseudo-labels, which greatly reduces the cost of annotation. Since CNN cannot fully identify object regions, researchers found that Vision Transformers (ViT) can complement the deficiencies of CNN by better extracting global contextual information. However, ViT also introduces the problem of over-smoothing. Great progress has been made in recent years to solve the over-smoothing problem, yet two issues remain. The first issue is that the high-confidence regions in the network-generated CAM still contain areas irrelevant to the class. The second issue is the inaccuracy of CAM boundaries, which contain a small portion of background regions. As we know, the precision of label boundaries is closely tied to excellent segmentation performance. In this work, to address the first issue, we propose a local optimized cropping module (LOC). By randomly cropping selected regions, we allow the local class tokens to be contrasted with the global class tokens. This method facilitates enhanced consistency between local and global representations. To address the second issue, we design a boundary enhancement module (BE) that utilizes an erasing strategy to re-train the image, increasing the network's extraction of boundary information and greatly improving the accuracy of CAM boundaries, thereby enhancing the quality of pseudo labels. Experiments on the PASCAL VOC dataset show that the performance of our proposed LOC-BE Net outperforms multi-stage methods and is competitive with end-to-end methods. On the PASCAL VOC dataset, our method achieves a CAM mIoU of 74.2% and a segmentation mIoU of 73.1%. On the COCO2014 dataset, our method achieves a CAM mIoU of 43.8% and a segmentation mIoU of 43.4%. Our code has been open sourced: https://***/whn786/LOC-BE/tree/main.

关键词： Deep learning weakly-supervised semantic segmentation Computer vision Single-stage Boundary enhancement Local optimization cropping

来源：评论

学校读者我要写书评

暂无评论

SCC-CAM: weakly supervised segmentation on Brain Tumor MRI with Similarity Constraint and Causality 7th

SCC-CAM: Weakly Supervised Segmentation on Brain Tumor MRI w...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Jiao, Panpan Tian, Zhiqiang Chen, Zhang Guo, Xuejian Chen, Zhi Dou, Liang Du, Shaoyi Xi An Jiao Tong Univ Sch Software Engn Xian Shaanxi Peoples R China Ecovacs Robot Co Ltd Suzhou Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian Shaanxi Peoples R China

ISBN: (纸本)9789819784899;9789819784905

This paper introduces SCC-CAM, a novel weakly supervised segmentation (WSSS) method for medical images. Transformer-based methods frequently face challenges like over-activation and inaccuracy in generating class attention maps (CAM), especially noticeable in medical images. We found that the attention mechanism tends to create excessive similarity among patch tokens, leading to over-activation in class attention maps. Moreover, potential confounders in medical images severely impair the localization of classes. To tackle these challenges, we propose a method named SCC-CAM based on similarity constraint and causality for generating class attention maps. This method directly constrains the similarity between patch tokens to guide the precise localization of objects. Additionally, we remove the influence of potential confounders by introducing causal theory, further enhancing the accuracy of results. Compared to other WSSS methods, our SCC-CAM achieves the best pseudo masks with Dice scores of 68.2%, 72.8% and 77.1% on the T1, T2 and T2-FLAIR modalities of the BraTS 2021 dataset. The evaluation on the BraTS 2021 dataset demonstrates the effectiveness and superiority of our proposed method.

关键词： Causal intervention Brain tumor segmentation weakly-supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Which CAM is Better for Extracting Geographic Objects? A Perspective From Principles and Experiments

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 5623-5635页

作者： Su, Qi Zhang, Xueliang Xiao, Pengfeng Li, Zhenshi Wang, Wenye Nanjing Univ Sch Geog & Ocean Sci Minist Nat ResourcesKey Lab Land Satellite Remot Jiangsu Prov Key Lab Geog Informat Sci & Technol Nanjing 210023 Peoples R China

As a method of deep learning interpretability, class activation mapping (CAM) is efficient and convenient for extracting geographic objects supervised by image-level labels. However, in addition to the inherent problem of inaccuracy and incompleteness of CAM, we have to deal with the spectral and spatial variance of geographic objects when applying CAM methods to remote sensing images. To explore the capabilities of CAM methods on extracting various geographic objects, we make a comprehensive comparison of five commonly-used CAM methods, including original CAM, GradCAM, GradCAM++, SmoothGradCAM++, and ScoreCAM, in four aspects: efficiency;accuracy;effectiveness on dealing with the spectral and spatial variance;and performance of delineating different geographic object categories. The results demonstrate that the original CAM, GradCAM, and GradCAM++ achieves the highest efficiency, accuracy, and integrity for extracting geographic objects, respectively, which can help us choose the appropriate CAM methods according to the specific requirements of different extraction tasks. Benefiting from the capability in extracting various geographic objects and adaptability in complex scenes, GradCAM achieves the best performance in dealing with the spectral and spatial variance problem and shows the advantage of capturing object details and keeping object completeness at the same time. In addition to the comparison experiments and suggestions, we also provide the principle explanations of the performance differences. The findings of this article could contribute to a deep understanding of different CAM methods and benefit to selecting suitable CAM methods for extracting geographic objects from the perspectives of both principles and experiments.

关键词： Feature extraction Remote sensing Convolutional neural networks Task analysis Heating systems Data mining Training Class activation mapping (CAM) convolutional neural network (CNN) deep learning geographic objects weakly-supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

TRL: Transformer based refinement learning for hybrid-supervised semantic segmentation

引用

PATTERN RECOGNITION LETTERS 2022年 164卷 239-245页

作者： Cheng, Lin Fang, Pengfei Yan, Yan Lu, Yang Wang, Hanzi Xiamen Univ Sch Informat Fujian Key Lab Sensing & Comp Smart City Xiamen 361005 Peoples R China Australian Natl Univ Coll Engn & Comp Sci Canberra ACT 2601 Australia

This paper studies a new yet practical setting of semi-supervised semantic segmentation, i.e., hybrid-supervised semantic segmentation, where a small number of pixel-level (strong) annotations and a large number of image-level (weak) annotations are provided. It is a common practice to utilize pseudo labels to mitigate the issue of lacking strong annotations. However, most of the existing works focus on improving the model representation with unlabeled data, while ignoring the quality of pseudo labels, leading to poor segmentation performance. It is difficult to directly learn a model with limited images to produce high-quality pseudo labels. To address this problem, we propose a novel learning method, i.e., Transformer based Refinement Learning (TRL), which explores a learning process under the assistance of weak annotations and the supervision of strong annotations. TRL progressively refines heat maps from the poor qualities to the better ones to obtain satisfactory pseudo labels. Specifically, we propose a Dual-Cross Transformer Network (DCTN) to perform the refinement learning. DCTN extracts the features from both images and heat maps by a dual-stream network. The cross attentions inside DCTN hierarchically fuse the dual-stream features. The experiments on the PASCAL VOC and COCO datasets show that TRL outperforms the state-of-the-art methods for hybrid-supervised semantic segmentation. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Hybrid-supervised semantic segmentation Simi-supervised semantic segmentation weakly-supervised semantic segmentation Refinement learning Heat map Pseudo label

来源：评论

学校读者我要写书评

暂无评论

TPRO: Text-Prompting-Based weakly supervised Histopathology Tissue segmentation 26th

TPRO: Text-Prompting-Based Weakly Supervised Histopathology ...

引用

26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

作者： Zhang, Shaoteng Zhang, Jianpeng Xie, Yutong Xia, Yong Northwestern Polytech Univ Ningbo Inst Ningbo 315048 Peoples R China Northwestern Polytech Univ Sch Comp Sci & Engn Natl Engn Lab Integrated Aero Space Ground Ocean Xian 710072 Peoples R China Univ Adelaide Australian Inst Machine Learning Adelaide SA Australia Northwestern Polytech Univ Inst Res & Dev Shenzhen 518057 Peoples R China

ISBN: (纸本)9783031439063;9783031439070

Most existing weakly-supervised segmentation methods rely on class activation maps (CAM) to generate pseudo-labels for training segmentation models. However, CAM has been criticized for highlighting only the most discriminative parts of the object, leading to poor quality of pseudo-labels. Although some recent methods have attempted to extend CAM to cover more areas, the fundamental problem still needs to be solved. We believe this problem is due to the huge gap between image-level labels and pixel-level predictions and that additional information must be introduced to address this issue. Thus, we propose a text-prompting-based weakly supervised segmentation method (TPRO), which uses text to introduce additional information. TPRO employs a vision and label encoder to generate a similarity map for each image, which serves as our localization map. Pathological knowledge is gathered from the internet and embedded as knowledge features, which are used to guide the image features through a knowledge attention module. Additionally, we employ a deep supervision strategy to utilize the network's shallow information fully. Our approach outperforms other weakly supervised segmentation methods on benchmark datasets LUAD-HistoSeg and BCSS-WSSS datasets, setting a new state of the art. Code is available at: https://***/zhangst431/TPRO.

关键词： Histopathology Tissue segmentation weakly-supervised semantic segmentation Vision-Language

来源：评论

学校读者我要写书评

暂无评论

AME-CAM: Attentive Multiple-Exit CAM for weakly supervised segmentation on MRI Brain Tumor 26th

AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised S...

引用

26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

作者： Chen, Yu-Jen Hu, Xinrong Shi, Yiyu Ho, Tsung-Yi Natl Tsing Hua Univ Hsinchu Taiwan Univ Notre Dame Notre Dame IN 46556 USA Chinese Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9783031439063;9783031439070

Magnetic resonance imaging (MRI) is commonly used for brain tumor segmentation, which is critical for patient evaluation and treatment planning. To reduce the labor and expertise required for labeling, weakly-supervised semantic segmentation (WSSS) methodswith class activation mapping (CAM) have been proposed. However, existing CAM methods suffer from low resolution due to strided convolution and pooling layers, resulting in inaccurate predictions. In this study, we propose a novel CAM method, AttentiveMultiple-Exit CAM (AME-CAM), that extracts activation maps from multiple resolutions to hierarchically aggregate and improve prediction accuracy. We evaluate our method on the BraTS 2021 dataset and show that it outperforms state-of-the-art methods.

关键词： Tumor segmentation weakly-supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

From text to mask: Localizing entities using the attention of text-to-image diffusion models

引用

NEUROCOMPUTING 2024年 610卷

作者： Xiao, Changming Yang, Qi Zhou, Feng Zhang, Changshui Tsinghua Univ THUAI Inst Artificial Intelligence Beijing 100084 Peoples R China Beijing Natl Res Ctr Informat Sci & Technol BNRist Beijing 100084 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Aibee Inc Algorithm Res Beijing Peoples R China

Diffusion models have revolted the field of text-to-image generation recently. The unique way of fusing text and image information contributes to their remarkable capability of generating highly text-related images. From another perspective, these generative models imply clues about the precise correlation between words and pixels. This work proposes a simple but effective method to utilize the attention mechanism in the denoising network of text-to-image diffusion models. Without additional training time nor inference-time optimization, the semantic grounding of phrases can be attained directly. We evaluate our method on Pascal VOC 2012 and Microsoft COCO 2014 under weakly-supervised semantic segmentation setting and our method achieves superior performance to prior methods. In addition, the acquired word-pixel correlation is generalizable for the learned text embedding of customized generation methods, requiring only a few modifications. To validate our discovery, we introduce a new practical task called "personalized referring image segmentation" with a new dataset. Experiments in various situations demonstrate the advantages of our method compared to strong baselines on this task. In summary, our work reveals a novel way to extract the rich multi-modal knowledge hidden in diffusion models for segmentation.

关键词： Diffusion model for segmentation Text-image correlation weakly-supervised semantic segmentation Personalized recognition

来源：评论

学校读者我要写书评

暂无评论

Dense regression activation maps for lesion segmentation in CT scans of COVID-19 patients

引用

MEDICAL IMAGE ANALYSIS 2023年 86卷 102771页

作者： Xie, Weiyi Jacobs, Colin Charbonnier, Jean-Paul van Ginneken, Bram Radboudumc Dept Radiol & Nucl Med Diagnost Image Anal Grp NL-6525 GA Nijmegen Netherlands Thirona NL-6525 EC Nijmegen Netherlands

Automatic lesion segmentation on thoracic CT enables rapid quantitative analysis of lung involvement in COVID-19 infections. However, obtaining a large amount of voxel-level annotations for training segmentation networks is prohibitively expensive. Therefore, we propose a weakly-supervised segmentation method based on dense regression activation maps (dRAMs). Most weakly-supervised segmentation approaches exploit class activation maps (CAMs) to localize objects. However, because CAMs were trained for classification, they do not align precisely with the object segmentations. Instead, we produce high-resolution activation maps using dense features from a segmentation network that was trained to estimate a per-lobe lesion percentage. In this way, the network can exploit knowledge regarding the required lesion volume. In addition, we propose an attention neural network module to refine dRAMs, optimized together with the main regression task. We evaluated our algorithm on 90 subjects. Results show our method achieved 70.2% Dice coefficient, substantially outperforming the CAM-based baseline at 48.6%. We published our source code at https://github. com/DIAGNijmegen/bodyct-dram.

关键词： weakly-supervised semantic segmentation Class activation map Dense regression activation map COVID-19 Computed tomography Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Learning Whole-Slide segmentation from Inexact and Incomplete Labels Using Tissue Graphs 24th

Learning Whole-Slide Segmentation from Inexact and Incomplet...

引用

International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

作者： Anklin, Valentin Pati, Pushpak Jaume, Guillaume Bozorgtabar, Behzad Foncubierta-Rodriguez, Antonio Thiran, Jean-Philippe Sibony, Mathilde Gabrani, Maria Goksel, Orcun IBM Res Europe Zurich Switzerland Swiss Fed Inst Technol Zurich Switzerland Ecole Polytech Fed Lausanne Lausanne Switzerland Cochin Hosp Paris France Univ Paris Paris France Uppsala Univ Uppsala Sweden

ISBN: (纸本)9783030871963;9783030871956

Segmenting histology images into diagnostically relevant regions is imperative to support timely and reliable decisions by pathologists. To this end, computer-aided techniques have been proposed to delineate relevant regions in scanned histology slides. However, the techniques necessitate task-specific large datasets of annotated pixels, which is tedious, time-consuming, expensive, and infeasible to acquire for many histology tasks. Thus, weakly-supervised semantic segmentation techniques are proposed to leverage weak supervision which is cheaper and quicker to acquire. In this paper, we propose SegGini, a weakly-supervised segmentation method using graphs, that can utilize weak multiplex annotations, i.e., inexact and incomplete annotations, to segment arbitrary and large images, scaling from tissue microarray (TMA) to whole slide image (WSI). Formally, SegGini constructs a tissue-graph representation for an input image, where the graph nodes depict tissue regions. Then, it performs weakly-supervised segmentation via node classification by using inexact image-level labels, incomplete scribbles, or both. We evaluated SegGini on two public prostate cancer datasets containing TMAs and WSIs. Our method achieved state-of-the-art segmentation performance on both datasets for various annotation settings while being comparable to a pathologist baseline. Code and models are available at: https://***/histocartography/seg-gini.

关键词： weakly-supervised semantic segmentation Scalable digital pathology Multiplex annotations Graphs in digital pathology

来源：评论

学校读者我要写书评

暂无评论

PUZZLE-CAM: IMPROVED LOCALIZATION VIA MATCHING PARTIAL AND FULL FEATURES

PUZZLE-CAM: IMPROVED LOCALIZATION VIA MATCHING PARTIAL AND F...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Jo, Sanghyun Yu, In-Jae GYNetworks Incheon South Korea Korea Adv Inst Sci & Technol Sch Comp Daejeon South Korea

ISBN: (纸本)9781665441155

weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision. Most advanced approaches are based on class activation maps (CAMs) to generate pseudo-labels to train the segmentation network. The main limitation of WSSS is that the process of generating pseudo-labels from CAMs that use an image classifier is mainly focused on the most discriminative parts of the objects. To address this issue, we propose Puzzle-CAM, a process that minimizes differences between the features from separate patches and the whole image. Our method consists of a puzzle module and two regularization terms to discover the most integrated region in an object. Puzzle-CAM can activate the overall region of an object using image-level supervision without requiring extra parameters. In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 dataset. Code associated with our experiments is available at https://***/OFRIN/PuzzleCAM.

关键词： Image segmentation Deep learning Neural Networks weakly-supervised semantic segmentation

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：