检索结果-内蒙古大学图书馆

object localization in Highly Cluttered Environments Using Neural Network Learning on Microwave Scattering Data

MICROWAVE AND OPTICAL TECHNOLOGY LETTERS 2024年第11期66卷

作者： Jeong, Janghoon Park, Won-Kwang Son, Seong-Ho Soonchunhyang Univ Dept ICT Convergence Asan South Korea Kookmin Univ Dept Informat Secur Cryptog & Math Seoul South Korea Soonchunhyang Univ Dept Mech Engn Asan South Korea

Bifocusing-based microwave imaging is a promising direct imaging method for object localization in various applications. However, the method has the limitation that it only works well in environments with a homogenous background. In this paper, we present a direct microwave imaging method using a neural network (NN) model that can localize a small object even in highly cluttered environments with strong scatterers. The NN model is trained on some data sets obtained through multistatic measurements in a nonhomogeneous environment. To verify the approach, we prepared an experimental testbed equipped with a water tank containing 3 strong scatterers and 16 antennas to obtain 920 MHz multistatic scattering data. This experiment shows good localization performance, with an average localization error of approximately 4 mm (1/9 of a wavelength) over the entire experimental area, even in a strong scattering background.

关键词： artificial neural network bifocusing method microwave imaging object localization

来源：评论

学校读者我要写书评

暂无评论

CLIP-Driven Transformer for Weakly Supervised object localization

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2025年第6期47卷 4878-4896页

作者： Chen, Zhiwei Shen, Yunhang Cao, Liujuan Zhang, Shengchuan Ji, Rongrong Xiamen Univ Key Lab Multimedia Trusted Percept & Efficient Com Minist Educ China Xiamen 361005 Peoples R China Tencent Youtu Lab Shanghai 200233 Peoples R China

Weakly supervised object localization (WSOL) aims to localize objects using only image-level labels as supervision. Despite recent advancements incorporating transformers into WSOL have resulted in improvements, these methods often rely on category-agnostic attention maps, leading to suboptimal object localization. This paper presents a novel CLIP-Driven TRansformer (CDTR) that learns category-aware representations for accurate object localization. Specifically, we initially propose a Category-aware Stimulation Module (CSM) that embeds learnable category biases into self-attention maps, enhancing the learning process with auxiliary supervision. Additionally, an object Constraint Module (OCM) is designed to refine object regions in a self-supervised manner, leveraging the discriminative potential of the self-attention maps provided by CSM. To create a synergistic connection between CSM and OCM, we further develop a Semantic Kernel Integrator (SKI), which generates a semantic kernel for self-attention maps. Meanwhile, we explore the CLIP model and design a Semantic Boost Adapter (SBA) to enrich object representations by integrating semantic-specific image and text representations into self-attention maps. Extensive experimental evaluations on benchmark datasets, such as CUB-200-2011 and ILSVRC highlight the superior performance of our CDTR framework.

关键词： Location awareness Transformers Semantics Training Proposals Kernel Adaptation models Accuracy Visualization Reviews Weakly supervised learning object localization vision transformer

来源：评论

学校读者我要写书评

暂无评论

Rethinking erasing strategy on weakly supervised object localization

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2025年 135卷

作者： Fan, Yuming Wei, Shikui Tan, Chuangchuang Chen, Xiaotong Yang, Dongming Zhao, Yao Beijing Jiaotong Univ Inst Informat Sci Beijing 100044 Peoples R China Visual Intellgence X Int Cooperat Joint Lab MOE Inst Informat Sci Beijing Peoples R China ChinaTelecom Cloud Technol Co Ltd Beijing Peoples R China

Weakly supervised object localization (WSOL) is a challenging task that aims to locate object regions in images using image-level labels as supervision. Early research utilized erasing strategy to expand the localization regions. However, those methods usually adopt a fix threshold resulting in over- or under-fitting of the object region. Additionally, recent pseudo-label paradigm decouples the classification and localization tasks, causing confusion between foreground and background regions. In this paper, we propose the Soft-Erasing (SoE) method for Weakly Supervised object localization (WSOL). It includes two key modules: the Adaptive Erasing (AE) and Flip Erasing (FE). The AE module dynamically adjusts the erasing threshold using the object's structural information, while the noise information module ensures the classifier focuses on the foreground region. The FE module effectively decouples object and background information by using normalization and inversion techniques. Additionally, we introduce activation loss and reverse loss to strengthen semantic consistency in foreground regions. Experiments on public datasets demonstrate that our SoE framework significantly improves localization accuracy, achieving 70.86% on GT-Known Loc for ILSVRC and 95.84% for CUB-200-2011.

关键词： Weakly supervised learning Erasing strategy object localization

来源：评论

学校读者我要写书评

暂无评论

Learning Local Semantic Region Activations for Weakly Supervised object localization

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第10期34卷 10182-10193页

作者： Xu, Can Hui, Le Han, Yuehui Jiang, Haobo Chen, Jiaxin Xie, Jin Yang, Jian Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing 210093 Peoples R China Nanjing Univ Sch Intelligence Sci & Technol Nanjing 210093 Peoples R China

Weakly supervised object localization (WSOL) aims to train instance-level locators by exploiting accessible image-level labels. By multiplying channel-wise features with classification weights and then adding them together, most prior works follow the pipeline of the Class Activation Map (CAM) to collect the semantic responses, thereby highlighting regions that contribute to class prediction to achieve WSOL. However, CAM-based methods treat the class contributions of all pixel positions in a channel equally and assign dominant weights for the discriminative channels biasedly. This fails to express the fine-grained pixel-level semantic response of each channel and model the complex contextual relations between channels, resulting in the mixup of the activation value between non-discriminative foreground regions and the background. To alleviate these issues, we present a Local Semantic activation enhancement and Global Spatial correlation mining network (LSGS-Net) for accurate WSOL. Specifically, we first propose a local activation generation module to explicitly learn the semantic response of each pixel position from channels. Then, we design a regularization loss to supervise the consistency between similar local activations, which utilizes the cross-image information to improve the accuracy of local activations. We further propose a K-nearest Neighbors graph module to capture the spatial correlation between different local activations, which can adaptively assign more proper weights when fusing all local activation. In the inference stage, the bounding box will be determined with a foreground threshold. Extensive experiments show that LSGS-Net achieves significant and consistent improvement with various backbones on the CUB, ILSVRC, and OpenImages benchmarks, with a 97.5% and 75.3% GT-Known LOC on CUB and ILSVRC, respectively. For segmentation quality on OpenImages, LSGS-Net already exceeds the SOTA method by 1.2% pIoU and 1.9% PxAP.

关键词： Location awareness Semantics Correlation Feature extraction Task analysis Pipelines Proposals Weakly-supervised object localization spatial association semantic spatial activation

来源：评论

学校读者我要写书评

暂无评论

Discovering an inference recipe for weakly-supervised object localization

引用

PATTERN RECOGNITION 2024年 156卷

作者： Lee, Sanghuk Mun, Cheolhyun Uh, Youngjung Choe, Junsuk Byun, Hyeran Yonsei Univ Grad Sch Artificial Intelligence Seoul South Korea Yonsei Univ Dept Comp Sci Seoul South Korea Yonsei Univ Dept Appl Informat Engn Seoul South Korea Sogang Univ Dept Comp Sci & Engn Seoul South Korea

Most existing weakly-supervised object localization (WSOL) methods have improved training procedures for better localization performance. However, the inference procedure has been overlooked. We observe that the useful information for localization is missed by the current inference practice of WSOL. To address this limitation, we propose a new test-time ingredient for WSOL: binarizing the penultimate feature map and their corresponding weights of the last linear layer. With this simple remedy, the proposed method consistently improves the localization performance of the existing training methods for WSOL. Extensive evaluation including with three different backbone networks on three different WSOL benchmarks validates its effectiveness. In addition, we demonstrate our method is also able to improve weakly-supervised semantic segmentation performances on PASCAL VOC dataset. Lastly, since our method is only applied during the testing phase, our performance gain comes with negligible computational overheads.

关键词： object localization Weakly-supervised learning Semantic segmentation Test-time processing Binarization

来源：评论

学校读者我要写书评

暂无评论

Feature disparity learning for weakly supervised object localization

引用

IMAGE AND VISION COMPUTING 2024年 145卷

作者： Li, Bingfeng Ruan, Haohao Li, Xinwei Wang, Keping Henan Polytech Univ Sch Elect Engn & Automat Jiaozuo 454003 Peoples R China Henan Key Lab Intelligent Detect & Control Coal Mi Jiaozuo 454003 Peoples R China

Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. As a common WSOL method, adversarial erasing always masks the most discriminative region in the feature space to compel the network to localize more regions of the object. However, with the discriminative region vanishing, the localizer is confused when distinguishing the regions of object from the background. In this paper, we propose a new feature disparity learning (FDL), which encourages the network to learn more distinctive features from the object region with similarity measurement after feature enhancement. Specifically, we first introduce a Spatial Vector Cross Attention (SVCA) module. This module enhances responses in less discriminative region of erased feature maps by reintegrating the spatial distribution of features through the capture of interdependencies among spatial vectors on each channel. Furthermore, we propose a feature complementarity loss to measure the similarity between unerased features and erased features, guiding the network to learn feature disparities caused by adversarial erasing for improved localization and classification. Several experimental studies demonstrate a significant increase in localization performance over the existing state -of -the -art erasing methods on the CUB 200 - 2011 and ILSVRC 2016 datasets.

关键词： Weakly supervised learning object localization Adversarial erasing Spatial attention Similarity measure

来源：评论

学校读者我要写书评

暂无评论

Boosting Weakly Supervised object localization and Segmentation With Domain Adaption

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第12期46卷 8680-8695页

作者： Zhu, Lei She, Qi Chen, Qian Ren, Qiushi Lu, Yanye Peking Univ Hlth Sci Ctr Inst Med Technol Beijing 100191 Peoples R China Peking Univ Dept Biomed Engn Beijing 100871 Peoples R China Peking Univ Natl Biomed Imaging Ctr Beijing 100871 Peoples R China Shenzhen Bay Lab Inst Biomed Engn Shenzhen 5181071 Peoples R China Peking Univ Shenzhen Grad Sch Inst Biomed Engn Shenzhen 518055 Peoples R China ByteDance Beijing 100086 Peoples R China

Weakly supervised object localization (WSOL), adopting only image-level annotations to learn the pixel-level localization model, can release human resources in the annotation process. Most one-stage WSOL methods learn the localization model with multi-instance learning, making them only activate discriminative object parts rather than the whole object. In our work, we attribute this problem to the domain shift between the training and test process of WSOL and provide a novel perspective that views WSOL as a domain adaption (DA) task. Under this perspective, a DA-WSOL pipeline is elaborated to better assist WSOL with DA approaches by considering the specificities for the adaption of WSOL. Our DA-WSOL pipeline can discern the source-related and the Universum samples from other target samples based on a proposed target sampling strategy and then utilize them to solve the sample unbalancing and label unmatching between the source and target domain of WSOL. Experiments show that our pipeline outperforms SOTA methods on three WSOL benchmarks and can improve the performance of downstream weakly supervised semantic segmentation tasks.

关键词： Domain adaption object localization semantic segmentation weakly supervised learning

来源：评论

学校读者我要写书评

暂无评论

object localization Using Vision Transformer with a Loss Function Based on IOU and Mean Squared Error

Object Localization Using Vision Transformer with a Loss Fun...

引用

International Conference on Computational Science and Computational Intelligence (CSCI)

作者： Cheng, Hong Cheng, Wen Southern Arkansas Univ Dept Math & Comp Sci Magiolia AR 71753 USA

ISBN: (纸本)9798350361513;9798350372304

In this paper, we present a novel methodology employing a Vision Transformer coupled with a loss function derived from Intersection over Union (IOU) and Mean Squared Error (MSE) for precise object localization or bounding box regression. Through experimentation on two distinct datasets, we have observed that our custom loss function enhances the performance of ViT compared to alternative loss functions like Mean Square Error (MSE), LIoU, or LGIoU.

关键词： object localization box regression IOU GIOU LIOU LGIoU Vision Transformer Loss Function

来源：评论

学校读者我要写书评

暂无评论

Generalized Weakly Supervised object localization

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第4期35卷 5395-5406页

作者： Zhang, Dingwen Guo, Guangyu Zeng, Wenyuan Li, Lei Han, Junwei Northwestern Polytech Univ Sch Automat Brain & Artificial Intelligence Lab Xian 710129 Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei 230026 Peoples R China Sci & Technol Complex Syst Control & Intelligent Beijing 100074 Peoples R China

With the goal of learning to localize specific object semantics using the low-cost image-level annotation, weakly supervised object localization (WSOL) has been receiving increasing attention in recent years. Although existing literatures have studied a number of major issues in this field, one important yet challenging scenario, where the test object semantics may appear in the training phase (seen categories) or never been observed before (unseen categories), is still beyond the exploration of the existing works. We define this scenario as the generalized WSOL (GWSOL) and make a pioneering effort to study it in this article. By leveraging attribute vectors to associate seen and unseen categories, we involve threefold modeling components, i.e., the class-sensitive modeling, semantic-agnostic modeling, and content-aware modeling, into a unified end-to-end learning framework. Such design enables our model to recognize and localize unconstrained object semantics, learn compact and discriminative features that could represent the potential unseen categories, and customize content-aware attribute weights to avoid localizing on misleading attribute elements. To advance this research direction, we contribute the bounding-box manual annotations to the widely used AwA2 dataset and benchmark the GWSOL methods. Comprehensive experiments demonstrate the effectiveness of our proposed learning framework and each of the considered modeling components.

关键词： Location awareness Semantics Annotations Task analysis Feature extraction Training Manuals object localization unseen object category weakly supervised learning

来源：评论

学校读者我要写书评

暂无评论

Background Activation Suppression for Weakly Supervised object localization and Semantic Segmentation

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2024年第3期132卷 750-775页

作者： Zhai, Wei Wu, Pingyu Zhu, Kai Cao, Yang Wu, Feng Zha, Zheng-Jun Univ Sci & Technol China Hefei Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei Peoples R China

Weakly supervised object localization and semantic segmentation aim to localize objects using only image-level labels. Recently, a new paradigm has emerged by generating a foreground prediction map (FPM) to achieve pixel-level localization. While existing FPM-based methods use cross-entropy to evaluate the foreground prediction map and to guide the learning of the generator, this paper presents two astonishing experimental observations on the object localization learning process: For a trained network, as the foreground mask expands, (1) the cross-entropy converges to zero when the foreground mask covers only part of the object region. (2) The activation value continuously increases until the foreground mask expands to the object boundary. Therefore, to achieve a more effective localization performance, we argue for the usage of activation value to learn more object regions. In this paper, we propose a background activation suppression (BAS) method. Specifically, an activation map constraint module is designed to facilitate the learning of generator by suppressing the background activation value. Meanwhile, by using foreground region guidance and area constraint, BAS can learn the whole region of the object. In the inference phase, we consider the prediction maps of different categories together to obtain the final localization results. Extensive experiments show that BAS achieves significant and consistent improvement over the baseline methods on the CUB-200-2011 and ILSVRC datasets. In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets. Code and models are available at https://***/wpy1999/BAS-Extension.

关键词： Weakly supervised object localization Background activation suppression 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：