检索结果-内蒙古大学图书馆

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

ECT: Enhancement Cross Training for weakly supervised semantic segmentation 38

ECT: Enhancement Cross Training for Weakly Supervised Semant...

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Mai, Jiren Ma, Chenning Zhang, Congwei Yang, Wankou Southeast University School of Automation Nanjing China Beijing Institute of Remote Sensing Equipment Beijing China

ISBN: (纸本)9798350303636

In recent years, weakly supervised semantic segmentation (WSSS) has garnered significant attention, as it enables pixel-level segmentation using only image-level labels. However, current WSSS methods typically rely on extracting Class Activation Map (CAM) from a classification network as the initial localization cues, which are often narrow and fragmented. In this paper, we demonstrate that more regions can be activated by roughly applying enhancement functions on CAM. Specifically, we propose an Enhancement Cross Training (ECT) approach for WSSS, which involves non-learning enhancement functions and a Cross Training process for integrating enhancement functions into the learnable CAM generation network. By cross-training two identical CAM generation models, ECT allows CAM to expand with its own localization information. Experiment on PASCAL VOC 2012 shows that our method is competitive with existing state-of-the-art methods. © 2023 IEEE.

关键词： Class Activation Map Cross-Training Remapping weakly supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for weakly supervised semantic segmentation

Separate and Conquer: Decoupling Co-occurrence via Decomposi...

引用

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

作者： Yang, Zhiwei Fu, Kexue Duan, Minghong Qu, Linhao Wang, Shuo Song, Zhijian Fudan Univ Acad Engn & Technol Shanghai Peoples R China Fudan Univ Digital Med Res Ctr Sch Basic Med Sci Shanghai Peoples R China Shanghai Key Lab Med Image Comp & Comp Assisted I Shanghai Peoples R China Shandong Comp Sci Ctr Natl Supercomp Ctr Jinan Qingdao Peoples R China

ISBN: (纸本)9798350353013;9798350353006

weakly supervised semantic segmentation (WSSS) with image-level labels aims to achieve segmentation tasks without dense annotations. However, attributed to the frequent coupling of co-occurring objects and the limited supervision from image-level labels, the challenging co-occurrence problem is widely present and leads to false activation of objects in WSSS. In this work, we devise a 'Separate and Conquer' scheme SeCo to tackle this issue from dimensions of image space and feature space. In the image space, we propose to 'separate' the co-occurring objects with image decomposition by subdividing images into patches. Importantly, we assign each patch a category tag from Class Activation Maps (CAMs), which spatially helps remove the co-context bias and guide the subsequent representation. In the feature space, we propose to 'conquer' the false activation by enhancing semantic representation with multi-granularity knowledge contrast. To this end, a dual-teacher-single-student architecture is designed and tag-guided contrast is conducted, which guarantee the correctness of knowledge and further facilitate the discrepancy among co-contexts. We streamline the multi-staged WSSS pipeline end-to-end and tackle this issue without external supervision. Extensive experiments are conducted, validating the efficiency of our method and the superiority over previous single-staged and even multi-staged competitors on PASCAL VOC and MS COCO. Code is available here.

关键词： Class activation map Co-occurrence Contrastive learning weakly supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

引用

13th International Conference on Digital Image Processing (ICDIP)

作者： Zhang, Jinkai Yan, Hui Chen, Tao Nanjing Univ Sci & Technol Sch Sci & Technol Nanjing 210094 Jiangsu Peoples R China

ISBN: (数字)9781510646018

ISBN: (纸本)9781510646018

semantic segmentation with deep learning has achieved remarkable progress in classifying the pixels in the image. Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. Image-level label-based weakly supervised semantic segmentation (WSSS) aims to adopt image-level labels to train semantic segmentation models, saving vast human labors for costly pixel-level annotations. A typical pipeline for this problem is to adopt Class Activation Maps (CAMs) with image-level labels to generate pseudo-masks (a.k.a. seeds) and then use them for training segmentation models. The main difficulty is that seeds are usually sparse and incomplete. In recent years, GCNs have made great strides in various fields. GCN can perform global modeling and reasoning on the relationship between regions, which is beneficial for many computer vision tasks. This is our motivation to combine these two aspects. Therefore we propose the module of class-related graph convolution. Because there are differences between classes, our GCN is parallel. Each GCN can learn the class-related region extension strategy. To enable GCN to learn more authentic relationships, we also introduce the attention mechanisms. We conduct lots of experiments on the public PASCAL VOC dataset, and our model yields state-of-the-art performance.

关键词： graph convolution weakly supervised semantic segmentation class-related

来源：评论

学校读者我要写书评

暂无评论

Complementary branch fusing class and semantic knowledge for robust weakly supervised semantic segmentation

引用

PATTERN RECOGNITION 2024年 157卷

作者： Han, Woojung Kang, Seil Choo, Kyobin Hwang, Seong Jae Yonsei Univ Dept Comp Sci 50 Yonsei Ro Seoul 03722 South Korea Yonsei Univ Dept Artificial Intelligence 50 Yonsei Ro Seoul 03722 South Korea

Leveraging semantically precise pseudo masks derived from image-level class knowledge for segmentation, namely image-level weakly supervised semantic segmentation (WSSS), remains challenging. Class Activation Maps (CAMs) using CNNs enhance WSSS by focusing on specific class parts like only the face of a human, whereas Vision Transformers (ViT) capture broader semantic parts but often miss complete class-specific details, such as human bodies with nearby objects like dogs. In this work, we propose a Co mplementary Bra nch ( CoBra ), a novel dual-branch framework consisting of two distinct architectures that provide valuable complementary knowledge of class (from CNN) and semantics (from ViT). In particular, we learn Class-Aware Projection (CAP) for the CNN branch and semantic-Aware Projection (SAP) for the ViT branch, combining their insights to facilitate new patch-level supervision and create effective pseudo masks integrating class and semantic information. Extensive experiments qualitatively and quantitatively investigate how each branch complements the other, showing a significant result. Project Page and code are available: https://***/cobra2024/.

关键词： weakly supervised semantic segmentation Representation learning Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Road Friction Coefficient Estimation Via weakly supervised semantic segmentation and Uncertainty Estimation

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2022年第14期36卷 2258009-2258009页

作者： Liu, Feilin Wu, Yan Mo, Yujian Liao, Yujun He, Yufei Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China

Vision-based road friction coefficient estimation received extensive attention in the field of road maintenance and autonomous driving. However, the current mainstream coarse-grained friction estimation methods are basically based on image classification tasks. This makes it difficult to deal with complex road conditions in changing weathers. Many models can correctly predict the friction coefficients of the road as a whole in consistent and simple road conditions, but perform poorly otherwise. The existing image benchmarks in this field rarely consider the above problems as well, which limits the comparable evaluations of different models. Therefore, in this paper, we first construct a challenging pixel-level friction coefficient estimation dataset WRF-P to evaluate model performances under mixed road conditions. Then, we propose a friction coefficient estimation method based on weakly supervised learning and uncertainty estimation to realize pixel-level road friction prediction with low annotation cost. The model outperforms existing weakly supervised methods and reaches 39.63% mIOU on the WRF-P dataset. The WRF-P dataset will be made publicly available at https://***/blackholeLFL/The-WRF-dataset soon.

关键词： Road friction coefficient estimation weakly supervised semantic segmentation uncertainty estimation autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Multi-layered self-attention mechanism for weakly supervised semantic segmentation

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2024年 239卷

作者： Yaganapu, Avinash Kang, Mingon Univ Nevada Las Vegas Dept Comp Sci 4505 S Maryland Pkwy Las Vegas NV 89154 USA

weakly supervised semantic segmentation (WSSS) provides efficient solutions for semantic image segmen-tation using image-level annotations. WSSS requires no pixel-level labeling that Fully supervised semantic segmentation (FSSS) does, which is time-consuming and label-intensive. Most WSSS approaches have leveraged Class Activation Maps (CAM) or Self-Attention (SA) to generate pseudo pixel-level annotations to perform semantic segmentation tasks coupled with fully supervised approaches (e.g., Fully Convolutional Network). However, those approaches often provides incomplete supervision that mainly includes discriminative regions from the last convolutional layer. They may fail to capture regions of low-or intermediate-level features that may not be present in the last convolutional layer. To address the issue, we proposed a novel Multilayered Self-Attention (Multi-SA) method that applies a self-attention module to multiple convolutional layers, and then stack feature maps from the self-attention layers to generate pseudo pixel-level annotations. We demonstrated that integrated feature maps from multiple self-attention layers produce higher coverage in semantic segmentation than using only the last convolutional layer through intensive experiments using standard benchmark datasets.

关键词： weakly supervised semantic segmentation segmentation Self-attention Image-level labels

来源：评论

学校读者我要写书评

暂无评论

DCAM: Disturbed class activation maps for weakly supervised semantic segmentation

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2023年第1期94卷

作者： Lei, Jie Yang, Guoyu Wang, Shuaiwei Feng, Zunlei Liang, Ronghua Zhejiang Univ Technol Hangzhou 310014 Peoples R China Zhejiang Univ Hangzhou 310027 Peoples R China

In the field of weakly supervised semantic segmentation (WSSS), Class Activation Maps (CAM) are typically adopted to generate pseudo masks. Yet, we find that the crux of the unsatisfactory pseudo masks is the incomplete CAM. Specifically, as convolutional neural networks tend to be dominated by the specific regions in the high-confidence channels of feature maps during prediction, the extracted CAM contains only parts of the object. To address this issue, we propose the Disturbed CAM (DCAM), a simple yet effective method for WSSS. Following CAM, we adopt a binary cross-entropy (BCE) loss to train a multi-label classification model. Then, we disturb the feature map with retraining to enhance the high-confidence channels. In addition, a softmax cross-entropy (SCE) loss branch is employed to increase the model attention to the target classes. Once converged, we extract DCAM in the same way as in CAM. The evaluation on both PASCAL VOC and MS COCO shows that DCAM not only generates high-quality masks (6.2% and 1.4% higher than the benchmark models), but also enables more accurate activation in object regions. The code is available at https://***/gyyang23/DCAM.

关键词： weakly supervised semantic segmentation Class activation map Image-level class label Disturbance injection

来源：评论

学校读者我要写书评

暂无评论

TSD-CAM: transformer-based self distillation with CAM similarity for weakly supervised semantic segmentation

引用

JOURNAL OF ELECTRONIC IMAGING 2024年第2期33卷 023029-023029页

作者： Yan, Lingyu Chen, Jiangfeng Tang, Yuanyan Hubei Univ Technol Sch Comp Sci Wuhan Peoples R China Zhuhai UM Sci & Technol Res Inst Zhuhai Peoples R China

weakly supervised semantic segmentation (WSSS) using only image-level labels is a challenging task. Most existing methods utilize class activation map (CAM) to generate pixel-level pseudo labels for supervised training. However, the gap between classification and segmentation hinders the network from obtaining more comprehensive semantic information and generating more accurate pseudo masks for segmentation. To address this issue, we propose TSD-CAM, a transformer-based self distillation (SD) method that utilizes CAM similarity. TSD-CAM uses the similarity between CAMs generated from different views as a distillation target, providing additional supervision for the network and narrowing the gap between classification and segmentation. SD supervision allows the network to acquire more semantic information and refine CAMs to generate higher precision pseudo-labels. In addition, we propose the adaptive pixel refinement module, which adaptively refines and adjusts images based on pixel variations, further improving the precision of pseudo labels. Our method is a fully end-to-end single-stage approach that achieves state-of-the-art 71.3% mIoU on PASCAL VOC 2012 and 42.9% mIoU on the MS COCO 2014 dataset, and the proposed TSD-CAM can significantly outperform other single-stage competitors and achieve comparable performance with state-of-the-art multi-stage methods. Meanwhile, the effectiveness of our method is demonstrated by a large number of ablation experiments, and we provide a new way of thinking to solve the problems of WSSS. Our code is available at: https://***/pipizhum/TSD-CAM.

关键词： weakly supervised semantic segmentation class activation map transformer similarity self distillation

来源：评论

学校读者我要写书评

暂无评论

A Stepwise Refining Image-Level weakly supervised semantic segmentation Method for Detecting Exposed Surface for Buildings (ESB) From Very High-Resolution Remote Sensing Images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Huang, Xin Wang, Wenrui Li, Jiayi Wang, Leiguang Xie, Xing Wuhan Univ Sch Remote Sensing Informat Engn Wuhan 430079 Peoples R China Southwest Forestry Univ Inst Big Data & Artificial Intelligence Kunming Peoples R China Southwest Forestry Univ Key Lab State Forestry Grassland Adm Forestry & Ecol Big Data Kunming 650024 Peoples R China Suzhou Univ Sch Environm & Mapping Engn Suzhou 234000 Peoples R China

Exposed surface for buildings (ESB), which refers to exposed surfaces with traces of building construction, often leads to urban dust. Accurate ESB detection is important for planning urban development and improving urban environment. Fine-grained monitoring of ESB typically needs massive high-quality pixel-level labels, which are demanding and expensive. In contrast, obtaining cost-efficient image-level labels is more promising. Most image-level weakly supervised methods can extract pixel-level pseudo labels using the class activation map (CAM) generated by the classification network. Subsequently, these labels are applied to train the semantic segmentation network. However, the CAM is easy to miss fine-grained information, which leads to label noise. Moreover, the downsampling in the segmentation networks will further loss the spatial information. Furthermore, the sparse distribution and irregular shape of ESB pose additional challenges. Given these problems, we propose a stepwise refining image-level weakly supervised semantic segmentation method (SRIWS): 1) we introduce a new data augmentation method called SRMix to oversample the classification dataset;2) we propose a two-branch network with a superpixel pooling layer (SPNet) as the semantic segmentation network to capture both global semantic information and spatial details;and 3) to alleviate the impact of potential noise in the initial labels, we design the high-confidence sample filtering operation (HSF) during the SPNet training. The evaluation experiments for the SRIWS were performed on three datasets. The results confirm that our proposed SRIWS presents a superior performance in recognizing ESB compared with existing state-of-the-art methods. In addition, numerous ablation experimental results indicate the effectiveness and robustness of our SRIWS.

关键词： Exposed surface for buildings (ESB) image-level samples very high-resolution remote sensing (VHR) images 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：