检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Fang, Jingyuan Ning, Yang Nie, Xiushan School of Computer Science and Technology Shandong Jianzhu University Jinan China

ISBN: (纸本)9798350368741

weakly-supervised semantic segmentation (WSSS) aims to achieve pixel-level classification under image-level supervision. Recent class activation map (CAM)-based methods seek to expand foreground activation while suppressing background. However, they often overlook the uncertainty of CAM, where non-salient activation in some regions complicates semantic classification. These regions are typically dismissed as noise, resulting in inappropriate activations due to inadequate regularization. To resolve this, we introduce a Spatial Frequency-Aware Self-Distillation strategy (SFS). Firstly, to enhance the perception of high-frequency spatial information in uncertain regions, we propose a boundary self-distillation and uncertain region reconstruction strategy, which captures high-frequency boundary information and fine-grained spatial context in these regions. Secondly, to enhance the discrimination of low-frequency semantic features, we propose a contrastive attention mechanism that guides the Vision Transformer (ViT) to focus more on the foreground, thereby improving the distinction between foreground and background. Finally, our SFS demonstrates outstanding performance on both the VOC 2012 and COCO 2014 datasets, attributed to its superior spatial frequency perception capabilities. The code is available at https://***/fjoybest/SFS. © 2025 IEEE.

关键词： self-distillation spatial frequency awareness weakly-supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhancing weakly supervised semantic segmentation with efficient and robust neighbor-attentive superpixel aggregation

引用

IMAGE AND VISION COMPUTING 2025年 154卷

作者： Wang, Chen Ma, Huifang Zhang, Di Li, Xiaolong Li, Zhixin Northwest Normal Univ Coll Comp Sci & Engn Lanzhou 730070 Gansu Peoples R China Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin 541004 Guangxi Peoples R China Key Lab Cloud Comp Gansu Prov Lanzhou 730070 Gansu Peoples R China

Image-level weakly-supervised semantic segmentation (WSSS) has become prominent as a technique that utilizes readily available image-level supervisory information. However, traditional methods that rely on pseudo-segmentation labels derived from Class Activation Maps (CAMs) are limited in terms of segmentation accuracy, primarily due to the incomplete nature of CAMs. Despite recent advancements in improving the comprehensiveness of CAM-derived pseudo-labels, challenges persist in handling ambiguity at object boundaries, and these methods also tend to be computationally intensive. To address these challenges, we propose a novel framework called Neighbor-Attentive Superpixel Aggregation (NASA). Inspired by the effectiveness of superpixel segmentation in homogenizing images through color and texture analysis, NASA enables the transformation from superpixel-wise to pixel-wise pseudo-labels. This approach significantly reduces semantic uncertainty at object boundaries and alleviates the computational overhead associated with direct pixel-wise label generation from CAMs. Besides, we introduce a superpixel augmentation strategy to enhance the model's discrimination capabilities across different superpixels. Empirical studies demonstrate the superiority of NASA over existing WSSS methodologies. On the PASCAL VOC 2012 and MS COCO 2014 datasets, NASA achieves impressive mIoU scores of 73.5% and 46.4%, respectively.

关键词： weakly-supervised semantic segmentation Superpixel segmentation Graph convolutional networks

来源：评论

学校读者我要写书评

暂无评论

weakly-supervised semantic segmentation with Visual Words Learning and Hybrid Pooling

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2022年第4期130卷 1127-1144页

作者： Ru, Lixiang Du, Bo Zhan, Yibing Wu, Chen Wuhan Univ Natl Engn Res Ctr Multimedia Software Inst Artificial Intelligence Sch Comp Sci Wuhan Peoples R China Wuhan Univ Hubei Key Lab Multimedia & Network Commun Engn Wuhan Peoples R China JD Explore Acad JDcom Beijing Peoples R China Wuhan Univ LIESMARS Wuhan Peoples R China

weakly-supervised semantic segmentation (WSSS) methods with image-level labels generally train a classification network to generate the Class Activation Maps (CAMs) as the initial coarse segmentation labels. However, current WSSS methods still perform far from satisfactorily because their adopted CAMs (1) typically focus on partial discriminative object regions and (2) usually contain useless background regions. These two problems are attributed to the sole image-level supervision and aggregation of global information when training the classification networks. In this work, we propose the visual words learning module and hybrid pooling approach, and incorporate them in classification network to mitigate the above problems. In visual words learning module, we counter the first problem by enforcing the classification network to learn fine-grained visual word labels so that more object extents could be discovered. Specifically, the visual words are learned with a codebook, which could be updated via two proposed strategies, i.e. learning-based strategy and memory-bank strategy. The second drawback of CAMs is alleviated with the proposed hybrid pooling, which incorporates the global average and local discriminative information to simultaneously ensure object completeness and reduce background regions. We evaluated our methods on PASCAL VOC 2012 and MS COCO 2014 datasets. Without any extra saliency prior, our method achieved 70.6% and 70.7% mIoU on the val and test set of PASCAL VOC dataset, respectively, and 36.2% mIoU on the val set of MS COCO dataset, which significantly surpassed the performance of state-of-the-art WSSS methods.

关键词： weakly-supervised semantic segmentation Visual words learning Hybrid pooling semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

weakly-supervised semantic segmentation via Label Re-assignment in Dual-View Framework 33rd

Weakly-Supervised Semantic Segmentation via Label Re-assignm...

引用

33rd International Conference on Artificial Neural Networks and Machine Learning (ICANN)

作者： Wang, Chen Zhang, Di Li, Xiaolong Ma, Huifang Li, Zhixin Northwest Normal Univ Coll Comp Sci & Engn Lanzhou Peoples R China Key Lab Cloud Comp Gansu Prov Lanzhou Peoples R China Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin Peoples R China

ISBN: (纸本)9783031723377;9783031723384

Mining accurate Class Activation Maps (CAMs) is essential for weakly-supervised semantic segmentation (WSSS). However, the CAMs only activate the most discriminative semantic regions, which can severely affect the segmentation results. Motivated by the observation that local image can capture more details, we propose a Dual-view Label Re-assignment (DLR) framework aiming at the problems of incomplete objects and unclear boundaries in pseudo-labels. Specifically, we first extract comprehensive features and intricate features from global views and local views. In order to take advantage of these features, we further incorporate two additional components, Local View Constraint (LVC) and Foreground-Background Contrast (FBC). LVC facilitates the complementary learning of global and local features through feature transfer loss. FBC enhances boundaries by intensifying the distinction between foreground and background. Experiments show the DLR achieve 1.5% and 3.9% mIoU improvements compared with other method on the validation set of PASCAL VOC 2012 and MS COCO 2014, respectively.

关键词： weakly-supervised semantic segmentation Class Activation Maps Label Re-assignment

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning of Object-Aware Activation Map for weakly-supervised semantic segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第8期33卷 3935-3946页

作者： Chen, Junliang Lu, Weizeng Li, Yuexiang Shen, Linlin Duan, Jinming Shenzhen Univ Comp Vis Inst Sch Comp Sci & Software Engn Shenzhen 518060 Peoples R China Shenzhen Univ Shenzhen Inst Artificial Intelligence & Robot Soc Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Tencent Jarvis Lab Shenzhen 518057 Peoples R China Univ Birmingham Sch Comp Sci Birmingham B15 2TT England

Recent years have witnessed impressive advances in the area of weakly-supervised semantic segmentation (WSSS). However, most of existing approaches are based on class activation maps (CAMs), which suffer from the under-segmentation problem (i.e., objects of interest are segmented partially). Although a number of literature works have been proposed to tackle this under-segmentation problem, we argue that these solutions built on CAMs may not be optimal for the WSSS task. Instead, in this paper we propose a network based on the object-aware activation map (OAM). The proposed network, termed OAM-Net, consists of four loss functions (foreground loss, background loss, average pixel and consistency loss) which ensure exactness, completeness, compactness and consistency of segmented objects via adversarial training. Compared to conventional CAM-based methods, our OAM-Net overcomes the under-segmentation drawback and significantly improves segmentation accuracy with negligible computational cost. A thorough comparison between OAM-Net and CAM-based approaches is carried out on the PASCAL VOC2012 dataset, and experimental results show that our network outperforms state-of-the-art approaches by a large margin. The code will be available soon.

关键词： weakly-supervised semantic segmentation class activation map object-aware activation map

来源：评论

学校读者我要写书评

暂无评论

Incorporating Network Built-in Priors in weakly-supervised semantic segmentation

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2018年第6期40卷 1382-1396页

作者： Saleh, Fatemeh Sadat Aliakbarian, Mohammad Sadegh Salzmann, Mathieu Petersson, Lars Alvarez, Jose M. Gould, Stephen Australian Natl Univ Coll Engn & Comp Sci GPO Box 4 Canberra ACT 0200 Australia CSIRO Data61 Canberra ACT 0200 Australia Ecole Polytech Fed Lausanne CVLab CH-1015 Lausanne Switzerland

Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, this leads to poor localization accuracy. This problem, however, was alleviated by making use of objectness priors to generate foreground/background masks. Unfortunately these priors either require pixel-level annotations/bounding boxes, or still yield inaccurate object boundaries. Here, we propose a novel method to extract accurate masks from networks pre-trained for the task of object recognition, thus forgoing external objectness modules. We first show how foreground/background masks can be obtained from the activations of higher-level convolutional layers of a network. We then show how to obtain multi-class masks by the fusion of foreground/background ones with information extracted from a weakly-supervised localization network. Our experiments evidence that exploiting these masks in conjunction with a weakly-supervised training loss yields state-of-the-art tag-based weakly-supervised semantic segmentation results.

关键词： semantic segmentation weak annotations convolutional neural networks weakly-supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Co-attention dictionary network for weakly-supervised semantic segmentation

引用

NEUROCOMPUTING 2022年第0期486卷 272-285页

作者： Wan, Weitao Chen, Jiansheng Yang, Ming-Hsuan Ma, Huimin Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Univ Calif Merced Merced CA USA Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol Beijing 100084 Peoples R China Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China

In this paper, we propose the co-attention dictionary network (CODNet) for weakly-supervised semantic segmentation using only image-level class labels. The CODNet model exploits extra semantic information by jointly leveraging a pair of samples with common semantics through co-attention rather than processing them independently. The inter-sample similarities of spatially distributed deep features are computed to merge reference features through non-local connections. To discover similar patterns regardless of appearance variations, we propose to extract image representations by equipping the neural networks with dictionary learning which provides the universal basis elements for different images. Based on the CODNet model, we propose a multi-reference class activation map (MR-CAM) algorithm which generates semantic segmentation masks for a target image by jointly merging semantic cues from multiple reference images. Experimental results on the PASCAL VOC 2012 and MSCOCO benchmark data sets for weakly-supervised semantic segmentation show that the proposed algorithm performs favorably against the state-of-the-art methods.(c) 2021 Elsevier B.V. All rights reserved.

关键词： weakly-supervised semantic segmentation Dictionary learning Co-attention

来源：评论

学校读者我要写书评

暂无评论

A weakly-supervised semantic segmentation Approach Based on the Centroid Loss: Application to Quality Control and Inspection

引用

IEEE ACCESS 2021年 9卷 69010-69026页

作者： Yao, Kai Ortiz, Alberto Bonnin-Pascual, Francisco Univ Balearic Isl Dept Math & Comp Sci Palma De Mallorca 07122 Spain Inst Invest Sanitaria Illes Balears IDISBA Palma De Mallorca 07120 Spain

It is generally accepted that one of the critical parts of current vision algorithms based on deep learning and convolutional neural networks is the annotation of a sufficient number of images to achieve competitive performance. This is particularly difficult for semantic segmentation tasks since the annotation must be ideally generated at the pixel level. weakly-supervised semantic segmentation aims at reducing this cost by employing simpler annotations that, hence, are easier, cheaper and quicker to produce. In this paper, we propose and assess a new weakly-supervised semantic segmentation approach making use of a novel loss function whose goal is to counteract the effects of weak annotations. To this end, this loss function comprises several terms based on partial cross-entropy losses, being one of them the Centroid Loss. This term induces a clustering of the image pixels in the object classes under consideration, whose aim is to improve the training of the segmentation network by guiding the optimization. The performance of the approach is evaluated against datasets from two different industry-related case studies: while one involves the detection of instances of a number of different object classes in the context of a quality control application, the other stems from the visual inspection domain and deals with the localization of images areas whose pixels correspond to scene surface points affected by a specific sort of defect. The detection results that are reported for both cases show that, despite the differences among them and the particular challenges, the use of weak annotations do not prevent from achieving a competitive performance level for both.

关键词： Image segmentation Annotations semantics Tools Inspection Training Surgery Object recognition quality control and inspection weakly-supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Partial Image Texture Translation Using weakly-supervised semantic segmentation 11th

Partial Image Texture Translation Using Weakly-Supervised Se...

引用

11th JSAI International Symposium on Artificial Intelligence (JSAI-ISAI) / 13th International Workshop on Juris-Informatics (JURISIN)

作者： Benitez-Garcia, Gibran Shimoda, Wataru Matsuo, Shin Yanai, Keiji Univ Electrocommun Dept Informat 1-5-1 Chofugaoka Chofu Tokyo 1828585 Japan

ISBN: (纸本)9783030587901;9783030587895

The field of Neural Style Transfer (NST) has led to interesting applications that enables to transform the reality as human beings perceive. Particularly, NST for material translation aims to change the material (texture) of an object to a different material from a desired image. In order to generate more realistic results, in this paper, we propose a partial texture style transfer method by combining NST with semantic segmentation. The original NST algorithm changes the style of an entire image including the style of background even though the texture is contained only in object regions. Therefore, we segment target objects using a weakly supervised segmentation method, and transfer the material of the style image to only material-based segmented areas. As a result, we achieved partial style transfer for only specific object regions, which enables us to change materials of objects in a given image as we like. Furthermore, we analyze the material translation capability of state-of-the-art image-to-image (I2I) translation algorithms, including the conventional NST method of Gatys, WCT, StarGAN, MUNIT, and DRIT++. The analysis of our experimental results suggests that the conventional NST produces more realistic results than other I2I translation methods. Moreover, there are certain materials that are easier to synthesize than others.

关键词： Neural style transfer weakly-supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

IMAGE AUGMENTATION WITH CONTROLLED DIFFUSION FOR weakly-supervised semantic segmentation 49

IMAGE AUGMENTATION WITH CONTROLLED DIFFUSION FOR WEAKLY-SUPE...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wu, Wangyu Dai, Tianhong Huang, Xiaowei Ma, Fei Xiao, Jimin Univ Liverpool Xian Jiaotong Liverpool Merseyside England Univ Liverpool Liverpool Merseyside England Univ Aberdeen Aberdeen Scotland

ISBN: (纸本)9798350344868;9798350344851

weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using available images and their image-level labels. However, the quality of pseudo labels degrades significantly when the size of available dataset is limited. Thus, in this paper, we tackle this problem from a different view by introducing a novel approach called Image Augmentation with Controlled Diffusion (IACD). This framework effectively augments existing labeled datasets by generating diverse images through controlled diffusion, where the available images and image-level labels are served as the controlling information. Moreover, we also propose a high-quality image selection strategy to mitigate the potential noise introduced by the randomness of diffusion models. In the experiments, our proposed IACD approach clearly surpasses existing state-of-the-art methods. This effect is more obvious when the amount of available data is small, demonstrating the effectiveness of our method.

关键词： weakly-supervised semantic segmentation diffusion model high-quality image selection

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：