检索结果-内蒙古大学图书馆

CLIP-Driven Transformer for Weakly Supervised object localization

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

SelfLoc: High Quality Unsupervised object localization with Self-Prompt SAM 7th

SelfLoc: High Quality Unsupervised Object Localization with ...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Zhang, Jiaheng Wang, Xiandong Li, Conghui Chen, Longyi Wang, Shengke Ocean Univ China Qingdao Peoples R China

ISBN: (纸本)9789819788576;9789819788583

Recently, self-supervised methods based on self-supervised transformer features have demonstrated promising results in unsupervised object localization. However, obtaining exceptional semantic results remains a formidable challenge. The current approaches heavily rely on the similarity between patch-level features within an image, while lacking supervision from image-level information. Meanwhile, the Segment Anything Model (SAM) has demonstrated remarkable class-agnostic segmentation capabilities for arbitrary objects in images with sparse prompts like points. In this work, we propose SelfLoc, a simple yet effective self-supervised object localization method via integration with self-prompt SAM. Specifically, a self-prompt generator is designed to automatically generate sparse prompts based on an image's self-attention map. Simultaneously, an image-wise integration module is developed to enhance the coarse mask obtained from self-supervised features by leveraging the fine-grained segmentation results of SAM. Extensive experimental results demonstrate that the proposed method not only achieves state-of-the-art performance in unsupervised saliency detection and object discovery tasks, but also sets a new benchmark in unsupervised camouflaged object segmentation. The source code will be publicly available at https://***/Rogersiy/SelfLoc.

关键词： Unsupervised learning object localization SAM

来源：评论

学校读者我要写书评

暂无评论

Attention-Driven object Encoding and Multiscale Contextual Perception for Improved Cross-View object Geo-localization

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Song, Haoshuai Tong, Xiaochong Zhang, Xiaoyu Lei, Yaxian Li, He Guo, Congzhou Informat Engn Univ Inst Geospatial Informat Zhengzhou 450001 Peoples R China Intelligent Game & Decis Lab IGDL Beijing 100091 Peoples R China Dept Basic Informat Engn Univ Zhengzhou 450001 Peoples R China

Cross-view object geo-localization (CVOGL) is essential for applications like navigation and intelligent city management. By identifying objects in street-view/drone-view and precisely locating them in satellite imagery, more accurate geo-localization can be achieved compared to retrieval-based methods. However, existing approaches fail to account for query object shape/size and significant scale variations in remote sensing images. To address these limitations, we propose an attention-driven multiscale perception network (AMPNet) for cross-view geo-localization. AMPNet employs an attention-driven object encoding (ADOE) based on segmentation, which provides prior information to enable learning more discriminative representations of the query object. In addition, AMPNet introduces a cross-view multiscale perception (CVMSP) module that captures multiscale contextual information using varying convolution kernels, and applies an MLP to enhance channel-wise feature interactions. Experimental results demonstrate that AMPNet outperforms state-of-the-art methods in both ground-to-satellite and drone-to-satellite object localization tasks on a challenging dataset.

关键词： Location awareness Encoding Image segmentation Training Feature extraction Satellite images Convolution Data mining Accuracy Kernel Cross-view geo-localization multiscale perception object localization positional encoding

来源：评论

学校读者我要写书评

暂无评论

object localization Based on Proposal Fusion

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2017年第9期19卷 2105-2116页

作者： Tang, Sheng Li, Yu Deng, Lixi Zhang, Yongdong Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Traditional regression framework of object localization such as Overfeat often suffers from the problem of inaccurate scoring due to the separate scoring of classification network and regression network upon inconsistent regions. To tackle this problem, in this paper, we propose a novel object localization framework based on multiple complementary region proposal methods from the view of classification rather than regression. On top of our framework, we first combine multiple complementary region proposals during both training and testing as a means of data augmentation to generate more dense and reliable proposals for fusion, then achieve optimal compromise between complexity and efficiency through category clustering for bounding box sharing among similar categories, and finally propose a dense proposal fusion approach to merge dense region proposals near true object for fine-tuning of the final bounding box's coordinates and updating the confidence of fused proposals for final decision. Extensive experiments on the well-known large scale ILSVRC 2015 LOC dataset verify the effectiveness of our object localization framework.

关键词： Dense proposal fusion object localization object detection region proposal

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

object localization via evaluation multi-task learning

引用

NEUROCOMPUTING 2017年 253卷 34-41页

作者： Tian, Yan Wang, Huiyan Wang, Xun Zhejiang Gongshang Univ Sch Comp & Informat Engn Hangzhou Zhejiang Peoples R China

Research on Region Convolution Neural Network (RCNN) based object localization has recently witnessed rapid progress, but constrained by the size of the output convolution map, this method is unable to obtain exact object positions. In this paper, we present a multi-task learning approach on convolution neural network for object localization. Our model consists of 3 modules, respectively extracting shared features, generating low-level features, and fusing different levels information. We developed an algorithm for the nontrivial end-to-end training of this causal, cascaded structure. Finally, we demonstrated performance of the algorithm on the PASCAL VOC 2007 dataset and traffic scene dataset. Experiments show that our algorithm effectively and efficiently improved performance. (C) 2017 Elsevier B.V. All rights reserved.

关键词： object localization Edge information Multi-task network Deep learning Information fusion

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

object localization BY OPTIMIZING CONVOLUTIONAL NEURAL NETWORK DETECTION SCORE USING GENERIC EDGE FEATURES 24

OBJECT LOCALIZATION BY OPTIMIZING CONVOLUTIONAL NEURAL NETWO...

引用

24th IEEE International Conference on Image Processing (ICIP)

作者： Etemad, Elham Gao, Qigang Dalhousie Univ Fac Comp Sci Halifax NS Canada

ISBN: (纸本)9781509021758

In this research, we propose an object localization method to boost the performance of current object recognition techniques. This method utilizes the image edge information as a clue to determine the location of the objects. The Generic Edge Tokens (GETs) of the image are extracted based on the perceptual organization elements of human vision. These edge tokens are parsed according to the Best First Search algorithm to fine-tune the location of objects, where the objective function is the detection score returned by the Deep Convolutional Neural Network. We have evaluated our method on top of the RCNN object recognition method. The results on Pascal VOC 2007 and 2012 show improved object localization performance. We also present several cases where the proposed method works significantly more precisely than RCNN.

关键词： Best First Search Convolutional Neural Networks Generic Edge Tokens object localization RCNN

来源：评论

学校读者我要写书评

暂无评论

object localization with subpixel accuracy for automated microinjection

Object localization with subpixel accuracy for automated mic...

引用

IEEE International Conference on Mechatronics and Automation

作者： Wang, Zuobin Yang, Ming Almansa, Ana Li, Ruoya Cardiff Univ Mfg Engn Ctr Cardiff Wales PROFACTOR Res & Solut GmbH Dept Micro & Nanohandling & Integrat Seibersdorf Austria Biopred Int R&D Dept Rennes France

ISBN: (纸本)9781424408276

This paper presents techniques for object localization with subpixel accuracy in automated microinjection. The subpixel accuracy was achieved using pattern matching and curve fitting techniques for localization of reference patterns and Xenopus oocytes. The paper discusses the effect of noise on the accuracy of object localization and analyses the relationship between the standard deviations. A statistical analysis shows that pattern matching and curve fitting lessen the effect of noise on the determination of object position.

关键词： object localization microinjection pattern matching subpixel accuracy

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：