检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

3,317 篇 会议
3 篇 期刊文献

馆藏范围

3,320 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,915 篇 工学
- 1,820 篇 计算机科学与技术...
- 376 篇 软件工程
- 142 篇 机械工程
- 136 篇 光学工程
- 42 篇 生物工程
- 28 篇 信息与通信工程
- 11 篇 控制科学与工程
- 9 篇 电气工程
- 9 篇 电子科学与技术（可...
- 9 篇 化学工程与技术
- 9 篇 交通运输工程
- 8 篇 生物医学工程（可授...
- 7 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
- 4 篇 建筑学
- 3 篇 土木工程
- 3 篇 农业工程
174 篇 理学
- 136 篇 物理学
- 43 篇 生物学
- 29 篇 数学
- 16 篇 统计学（可授理学、...
- 10 篇 化学
29 篇 医学
- 28 篇 临床医学
- 3 篇 基础医学(可授医学...
15 篇 管理学
- 8 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 3 篇 工商管理
5 篇 法学
- 3 篇 社会学
- 2 篇 法学
2 篇 教育学
- 2 篇 教育学
2 篇 农学
1 篇 经济学

主题

1,179 篇 computer vision
801 篇 conferences
570 篇 training
484 篇 pattern recognit...
330 篇 computational mo...
279 篇 computer archite...
255 篇 visualization
180 篇 feature extracti...
160 篇 neural networks
153 篇 semantics
152 篇 task analysis
145 篇 cameras
143 篇 deep learning
140 篇 three-dimensiona...
139 篇 benchmark testin...
126 篇 low-level vision
117 篇 vision
115 篇 language
113 篇 image segmentati...
112 篇 estimation

机构

35 篇 tsinghua univ pe...
34 篇 univ sci & techn...
28 篇 shanghai ai lab ...
26 篇 chinese univ hon...
25 篇 university of sc...
25 篇 tsinghua univers...
24 篇 peng cheng labor...
23 篇 swiss fed inst t...
23 篇 swiss fed inst t...
23 篇 peng cheng lab p...
22 篇 zhejiang univ pe...
22 篇 carnegie mellon ...
20 篇 univ chinese aca...
20 篇 university of ch...
18 篇 harbin inst tech...
18 篇 shanghai jiao to...
18 篇 sensetime res pe...
16 篇 hong kong univ s...
15 篇 fudan univ peopl...
14 篇 national key lab...

作者

60 篇 timofte radu
26 篇 radu timofte
19 篇 van gool luc
16 篇 lei lei
15 篇 loy chen change
15 篇 qiao yu
14 篇 fan haoqiang
13 篇 zhang yulun
13 篇 liu shuaicheng
13 篇 luc van gool
12 篇 chen chen
12 篇 chen wei-ting
12 篇 li chongyi
11 篇 wangmeng zuo
11 篇 pan jinshan
11 篇 marcos v. conde
10 篇 wei dong
10 篇 zhou shangchen
10 篇 suiyi zhao
10 篇 yu lei

语言

3,318 篇 英文
2 篇 其他

检索条件"任意字段=2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023"

共 3320 条记录，以下是2191-2200 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

SAM-CLIP: Merging vision Foundation Models towards Semantic and Spatial Understanding

SAM-CLIP: Merging Vision Foundation Models towards Semantic ...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Haoxiang Wang Pavan Kumar Anasosalu Vasu Fartash Faghri Raviteja Vemulapalli Mehrdad Farajtabar Sachin Mehta Mohammad Rastegari Oncel Tuzel Hadi Pouransari University of Illinois Urbana-Champaign Apple

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their pre-training objectives. For instance, CLIP excels in semantic understanding, while SAM specializes in spatial understanding for segmentation. In this work, we introduce a simple recipe to efficiently merge VFMs into a unified model that absorbs their expertise. Our method integrates techniques of multitask learning, continual learning, and distillation. Further, it demands significantly less computational cost compared to traditional multi-task training from scratch, and it only needs a small fraction of the pre-training datasets that were initially used to train individual models. By applying our method to SAM and CLIP, we obtain SAM-CLIP : a unified model that combines the capabilities of SAM and CLIP into a single vision transformer. Compared with deploying SAM and CLIP independently, our merged model, SAM-CLIP, reduces storage and compute costs for inference, making it well-suited for edge device applications. We show that SAM-CLIP not only retains the foundational strengths of SAM and CLIP, but also introduces synergistic functionalities, notably in zero-shot semantic segmentation, where SAM-CLIP establishes new state-of-the-art results on 5 benchmarks. It outperforms previous models that are specifically designed for this task by a large margin, including +6.8% and +5.9% mean IoU improvement on Pascal-VOC and COCO-Stuff datasets, respectively.

关键词： Training computer vision Visualization Computational modeling Semantic segmentation Semantics Merging

来源：评论

学校读者我要写书评

暂无评论

Key Patches Are All You Need: A Multiple Instance Learning Framework For Robust Medical Diagnosis

Key Patches Are All You Need: A Multiple Instance Learning F...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： D. J. Araújo M. R. Verdelho A. Bissoto J. C. Nascimento C. Santiago C. Barata LARSyS Instituto Superior Técnico Institute for Systems and Robotics Portugal Institute of Computing Recod.ai Lab University of Campinas Brazil Lisbon ELLIS Unit

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Deep learning models have revolutionized the field of medical image analysis, due to their outstanding performances. However, they are sensitive to spurious correlations, often taking advantage of dataset bias to improve results for in-domain data, but jeopardizing their generalization capabilities. In this paper, we propose to limit the amount of information these models use to reach the final classification, by using a multiple instance learning (MIL) framework. MIL forces the model to use only a (small) subset of patches in the image, identifying discriminative regions. This mimics the clinical procedures, where medical decisions are based on localized findings. We evaluate our framework on two medical applications: skin cancer diagnosis using dermoscopy and breast cancer diagnosis using mammography. Our results show that using only a subset of the patches does not compromise diagnostic performance for in-domain data, compared to the baseline approaches. However, our approach is more robust to shifts in patient demographics, while also providing more detailed explanations about which regions contributed to the decision. Code is available at: https://***/diogojpa99/Medical-Multiple-Instance-Learning.

关键词： Image analysis Pipelines MIMICs Focusing Breast cancer pattern recognition Mirrors

来源：评论

学校读者我要写书评

暂无评论

Probing Conceptual Understanding of Large Visual-Language Models

Probing Conceptual Understanding of Large Visual-Language Mo...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Madeline Schiappa Raiyaan Abdullah Shehreen Azad Jared Claypoole Michael Cogswell Ajay Divakaran Yogesh Rawat Center for Research in Computer Vision University of Central Florida SRI International

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

In recent years large visual-language (V+L) models have achieved great success in various downstream tasks. However, it is not well studied whether these models have a conceptual grasp of the visual content. In this work we focus on conceptual understanding of these large V+L models. To facilitate this study, we propose novel benchmarking datasets for probing three different aspects of content understanding, 1) relations, 2) composition, and 3) context. Our probes are grounded in cognitive science and help determine if a V+L model can, for example, determine if snow garnished with a man is implausible, or if it can identify beach furniture by knowing it is located on a beach. We experimented with many recent state-of-the-art V+L models and observe that these models mostly fail to demonstrate a conceptual understanding. This study reveals several interesting insights such as that cross-attention helps learning conceptual understanding, and that CNNs are better with texture and patterns, while Transformers are better at color and shape. We further utilize some of these insights and investigate a simple finetuning technique that rewards the three conceptual understanding measures with promising initial results. The proposed benchmarks will drive the community to delve deeper into conceptual understanding and foster advancements in the capabilities of large V+L models. The code and dataset is available at: https://***/vlm-robustness

关键词： Training Visualization Shape Snow Color Benchmark testing Transformers

来源：评论

学校读者我要写书评

暂无评论

Exploring AI-Based Satellite Pose Estimation: from Novel Synthetic Dataset to In-Depth Performance Evaluation

Exploring AI-Based Satellite Pose Estimation: from Novel Syn...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Fabien Gallet Christophe Marabotto Thomas Chambon Institut de Recherche Technologique Saint Exupéry

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

vision-based pose estimation using deep learning offers a promising cost effective and versatile solution for relative satellite navigation purposes. Using such a solution in closed loop to control spacecraft position is challenging from validation and performance verification viewpoint, because of the complex specification and development process. The validation task entails bridging the gap between the dataset and real-world data. In particular, modelling of Sun power and spectrum, Earth albedo, and atmospheric absence effects, is costly to replicate on ground. This article suggests a novel approach to produce synthetic space scene images. Fine statistical balancing is ensured to train and assess pose estimation solutions. A physically based camera model is used. Synthetic images incorporate realistic light flux, radiometric properties, and texture scatterings. The dataset comprises 120000 images supplemented with masks, distance maps, celestial body positions, and precise camera parameters (dataset publicly available https://***/space_rendezvous/ created in the frame of a project called RAPTOR: Robotic and Artificial intelligence Processing Test On Representative target). An analysis method using a dedicated metric library has been developed to help the assessment of the solution performance and robustness. A deeper comprehension of algorithm behavior through distribution law fitting and outlier identification is then facilitated. Finally, it is shown that implementing Region-of-Interest (RoI) training can drastically increase the performance of the Convolutional Neural Networks (CNNs) for long-range satellite pose estimation tasks.

关键词： Training Space vehicles computer vision Atmospheric modeling Pose estimation Satellite broadcasting Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

3D Clothed Human Reconstruction from Sparse Multi-View Images

3D Clothed Human Reconstruction from Sparse Multi-View Image...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Jin Gyu Hong Seung Young Noh Hee Kyung Lee Won Sik Cheong Ju Yong Chang Dept of ECE Kwangwoon University Seoul South Korea Electronics and Telecommunications Research Institute Daejeon South Korea

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Clothed human reconstruction based on implicit functions has recently received considerable attention. In this study, we explore the most effective 2D feature fusion method from multi-view inputs experimentally and propose a method utilizing the 3D coarse volume predicted by the network to provide a better 3D prior. We fuse 2D features using an attention-based method to obtain detailed geometric predictions. In addition, we propose depth and color projection networks that predict the coarse depth volume and the coarse color volume from the input RGB images and depth maps, respectively. Coarse depth volume and coarse color volume are used as 3D priors to predict occupancy and texture, respectively. Further, we combine the fused 2D features and 3D features extracted from our 3D prior to predict occupancy and propose a technique to adjust the influence of 2D and 3D features using learnable weights. The effectiveness of our method is demonstrated through qualitative and quantitative comparisons with recent multi-view clothed human reconstruction models.

关键词： Solid modeling computer vision Three-dimensional displays Image color analysis Fuses conferences Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Run-time Monitoring of 3D Object Detection in Automated Driving Systems Using Early Layer Neural Activation patterns

Run-time Monitoring of 3D Object Detection in Automated Driv...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Hakan Yekta Yatbaz Mehrdad Dianati Konstantinos Koufos Roger Woodman WMG University of Warwick School of Electronics Electrical Engineering and Computer Science (EEECS) Queen's University of Belfast

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Monitoring the integrity of object detection for errors within the perception module of automated driving systems (ADS) is paramount for ensuring safety. Despite recent advancements in deep neural network (DNN)-based object detectors, their susceptibility to detection errors, particularly in the less-explored realm of 3D object detection, remains a significant concern. State-of-the-art integrity monitoring (also known as introspection) mechanisms in 2D object detection mainly utilise the activation patterns in the final layer of the DNN-based detector’s backbone. However, that may not sufficiently address the complexities and sparsity of data in 3D object detection. To this end, we conduct, in this article, an extensive investigation into the effects of activation patterns extracted from various layers of the backbone network for introspecting the operation of 3D object detectors. Through a comparative analysis using Kitti and NuScenes datasets with PointPillars and CenterPoint detectors, we demonstrate that using earlier layers’ activation patterns enhances the error detection performance of the integrity monitoring system, yet increases computational complexity. To address the real-time operation requirements in ADS, we also introduce a novel introspection method that combines activation patterns from multiple layers of the detector’s backbone and report its performance.

关键词： computer vision Three-dimensional displays conferences Object detection Detectors Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

Event-Based Eye Tracking. AIS 2024 Challenge Survey

Event-Based Eye Tracking. AIS 2024 Challenge Survey

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Zuowen Wang Chang Gao Zongwei Wu Marcos V. Conde Radu Timofte Shih-Chii Liu Qinyu Chen Zheng-jun Zha Wei Zhai Han Han Bohao Liao Yuliang Wu Zengyu Wan Zhong Wang Yang Cao Ganchao Tan Jinze Chen Yan Ru Pei Sasskia Brüers Sébastien Crouzet Douglas McLelland Oliver Coenen Baoheng Zhang Yizhao Gao Jingyuan Li Hayden Kwok-Hay So Philippe Bich Chiara Boretti Luciano Prono Mircea Lică David Dinucu-Jianu Cătălin Grîu Xiaopeng Lin Hongwei Ren Bojun Cheng Xinan Zhang Valentin Vial Anthony Yezzi James Tsai Institute of Neuroinformatics University of Zurich and ETH Zurich Delft University of Technology University of Würzburg Leiden University University of Science and Technology of China Brainchip Inc The University of Hong Kong Polytechnic of Turin The Hong Kong University of Science and Technology (Guangzhou) Georgia Institute of Technology

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

This survey reviews the AIS 2024 Event-Based Eye Tracking (EET) Challenge. The task of the challenge focuses on processing eye movement recorded with event cameras and predicting the pupil center of the eye. The challenge emphasizes efficient eye tracking with event cameras to achieve good task accuracy and efficiency trade-off. During the challenge period, 38 participants registered for the Kaggle competition, and 8 teams submitted a challenge factsheet. The novel and diverse methods from the submitted factsheets are reviewed and analyzed in this survey to advance future event-based eye tracking research.

关键词： Surveys computer vision Visualization Reviews Gaze tracking Cameras Transformers

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods ...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Li, Yawei Zhang, Yulun Timofte, Radu Van Gool, Luc Yu, Lei Li, Youwei Li, Xinpeng Jiang, Ting Wu, Qi Han, Mingyan Lin, Wenjie Jiang, Chengzhi Luo, Jinting Fan, Haoqiang Liu, Shuaicheng Wang, Yucong Cai, Minjie Li, Mingxi Zhang, Yuhang Fan, Xian-Jun Sheng, Yankai Mao, Yanyu Zhang, Nihao Wang, Qian Zheng, Mingjun Sun, Long Pan, Jinshan Dong, Jiangxin Tang, Jinhui Yang, Zhongbao Wang, Yan Pan, Erlin Cai, Qixuan Dai, Xinan Zhussip, Magauiya Kalyazin, Nikolay Vyal, Dmitry Zou, Xueyi Yan, Youliang Chung, Heaseo Zhang, Jin Yu, Gaocheng Zhang, Feng Wang, Hongbin Liao, Bohao Du, Zhibo Wu, Yu-Liang Shi, Gege Peng, Long Wang, Yang Cao, Yang Zha, Zhengjun Huang, Zhi-Kai Chen, Yi-Chung Chiang, Yuan-Chun Yang, Hao-Hsiang Chen, Wei-Ting Chang, Hua-En Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Liu, Xin Pan, Jiahao Yu, Hongyuan Yu, Weichen Ge, Lin Dong, Jiahua Zou, Yajun Wu, Zhuoyuan Han, Binnan Zhang, Xiaolin Zhang, Heng Yin, Xuanwu Zuo, Kunlong Deng, Weijian Yuan, Hongjie Lu, Zengtong Ouyang, Mingyu Ma, Wenzhuo Liu, Nian Zheng, Hanyou Zhang, Yuantong Zhang, Junxi Chen, Zhenzhong Gendy, Garas Sabor, Nabil Hou, Jingchao He, Guanghui Zhu, Yurui Wang, Xi Fu, Xueyang Zha, Zheng-Jun Yin, Daheng Liu, Mengyang Chen, Baijun Li, Ao Luo, Lei Jin, Kangjun Zhu, Ce Zhang, Xiaoming Xie, Chengxing Li, Linze Meng, Haiteng Zhang, Tianlin Li, Tianrui Zhao, Xiaole Zhang, Zhao Li, Baiang Zheng, Huan Zhao, Suiyi Gao, Yangcheng Ren, Jiahuan Hu, Kang Shi, Jingpeng Wu, Zhijian Huang, Dingjiang Zhu, Jinchen Li, Hui Xv, Qianru Liu, Tianle Weng, Shizhuang Wu, Gang Jiang, Junpeng Liu, Xianming Jiang, Junjun Zhang, Mingjian Hu, Jing Wu, Chengxu Fan, Qinrui Feng, Chengming Luo, Ziwei Hu, Shu Lyu, Siwei Wu, Xi Wang, Xin Computer Vision Lab ETH Zurich Switzerland Computer Vision Lab University of Würzburg Germany Megvii Technology China MicroBT China College of Computer Science and Electronic Engineering Hunan University China Attrsense Xian University of Posts and Telecommunications Xi'an China National Engineering Laboratory for Cyber Event Warning and Control Technologies China Nanjing University of Science and Technology China Nankai University China University of Electronic Science and Technology of China China Tianjin University China Noah's Ark Lab Huawei Technologies McMaster University Canada Espresomedia Korea Republic of AntGroup China University of Science and Technology of China China Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taiwan ServiceNow United States China Mobile Research Institute China Chongqing University of Technology China Multimedia Department Xiaomi Inc. China Institute of Automation Chinese Academy of Sciences China Shenyang Institute of Automation Chinese Academy of Sciences China School of Information and Communication Engineering Communication University of China China Smart Classroom Division Ruijie Networks Co. Ltd. China School of Remote Sensing and Information Engineering Wuhan University China Micro-Nano Electronics Department Shanghai Jiao Tong University Shanghai200240 China Electrical Engineering Department Faculty of Engineering Assiut University Assiut71516 Egypt Southeast University China University of Electronic Science and Technology of China Chengdu China Chongqing University of Posts and Telecommunications Chongqing China Information Technology Co. Ltd Hangzhou China Southwest Jiaotong University China National Space Science Center Chinese Academy of Science China Hefei University of Technology Hefei China Anhui University China Fried Ric

ISBN: (纸本)9798350302493

This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects such as runtime, parameters, FLOPs, activations, memory footprint, and depth of RFDN while at least maintaining the PSNR of 29.00dB on DIV2K validation datasets. The challenge had 272 registered participants, and 35 teams made valid submissions. They gauge the state-of-the-art for efficient single-image super-resolution. © 2023 ieee.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Scaling Graph Convolutions for Mobile vision

Scaling Graph Convolutions for Mobile Vision

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： William Avery Mustafa Munir Radu Marculescu The University of Texas at Austin

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

To compete with existing mobile architectures, Mobile-ViG introduces Sparse vision Graph Attention (SVGA), a fast token-mixing operator based on the principles of GNNs. However, MobileViG scales poorly with model size, falling at most 1% behind models with similar latency. This paper introduces Mobile Graph Convolution (MGC), a new vision graph neural network (ViG) module that solves this scaling problem. Our proposed mobile vision architecture, Mobile-ViGv2, uses MGC to demonstrate the effectiveness of our approach. MGC improves on SVGA by increasing graph sparsity and introducing conditional positional encodings to the graph operation. Our smallest model, MobileViGv2-Ti, achieves a 77.7% top-1 accuracy on ImageNet-1K, 2% higher than MobileViG-Ti, with 0.9 ms inference latency on the iPhone 13 Mini NPU. Our largest model, MobileViGv2-B, achieves an 83.4% top-1 accuracy, 0.8% higher than MobileViG-B, with 2.7 ms inference latency. Besides image classification, we show that MobileViGv2 generalizes well to other tasks. For object detection and instance segmentation on MS COCO 2017, MobileViGv2-M outperforms MobileViG-M by 1.2 AP box and 0.7 AP mask , and MobileViGv2-B outperforms MobileViG-B by 1.0 AP box and 0.7 AP mask . For semantic segmentation on ADE20K, MobileViGv2-M achieves 42.9% mIoU and MobileViGv2-B achieves 44.3% mIoU 1 .

关键词： Instance segmentation Accuracy Convolution Semantic segmentation Message passing computer architecture Object detection

来源：评论

学校读者我要写书评

暂无评论

Feature Corrective Transfer Learning: End-to-End Solutions to Object Detection in Non-Ideal Visual Conditions

Feature Corrective Transfer Learning: End-to-End Solutions t...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Chuheng Wei Guoyuan Wu Matthew J. Barth University of California Riverside

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

A significant challenge in the field of object detection lies in the system’s performance under non-ideal imaging conditions, such as rain, fog, low illumination, or raw Bayer images that lack ISP processing. Our study introduces ‘Feature Corrective Transfer Learning’, a novel approach that leverages transfer learning and a bespoke loss function to facilitate the end-to-end detection of objects in these challenging scenarios without the need to convert non-ideal images into their RGB counterparts. In our methodology, we initially train a comprehensive model on a pristine RGB image dataset. Subsequently, non-ideal images are processed by comparing their feature maps against those from the initial ideal RGB model. This comparison employs the Extended Area Novel Structural Discrepancy Loss (EANSDL), a novel loss function designed to quantify similarities and integrate them into the detection loss. This approach refines the model’s ability to perform object detection across varying conditions through direct feature map correction, encapsulating the essence of Feature Corrective Transfer Learning. Experimental validation on variants of the KITTI dataset demonstrates a significant improvement in mean Average Precision (mAP), resulting in a 3.8-8.1% relative enhancement in detection under non-ideal conditions compared to the baseline model, and a less marginal performance difference within 1.3% of the mAP@[0.5:0.95] achieved under ideal conditions by the standard Faster RCNN algorithm.

关键词： Visualization computer vision Accuracy Computational modeling Surveillance Transfer learning Imaging

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共332页 << < 216 217 218 219 220 221 222 223 224 225 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：