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

3,854 篇 会议
1 篇 期刊文献

馆藏范围

3,855 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,938 篇 工学
- 2,846 篇 计算机科学与技术...
- 210 篇 软件工程
- 141 篇 机械工程
- 134 篇 光学工程
- 43 篇 生物工程
- 28 篇 信息与通信工程
- 10 篇 控制科学与工程
- 10 篇 交通运输工程
- 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
- 7 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
1,540 篇 医学
- 1,540 篇 临床医学
176 篇 理学
- 137 篇 物理学
- 44 篇 生物学
- 30 篇 数学
- 17 篇 统计学（可授理学、...
- 10 篇 化学
- 2 篇 大气科学
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...
- 4 篇 工商管理
6 篇 法学
- 4 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

2,497 篇 computer vision
1,153 篇 pattern recognit...
1,102 篇 training
834 篇 conferences
688 篇 computational mo...
531 篇 visualization
465 篇 computer archite...
429 篇 benchmark testin...
398 篇 semantics
377 篇 three-dimensiona...
362 篇 codes
307 篇 feature extracti...
297 篇 task analysis
296 篇 deep learning
262 篇 neural networks
226 篇 image segmentati...
221 篇 estimation
218 篇 object detection
212 篇 cameras
205 篇 measurement

机构

50 篇 univ sci & techn...
47 篇 tsinghua univ pe...
46 篇 peng cheng lab p...
42 篇 zhejiang univ pe...
41 篇 chinese univ hon...
39 篇 stanford univ st...
38 篇 swiss fed inst t...
38 篇 sensetime res pe...
37 篇 carnegie mellon ...
36 篇 swiss fed inst t...
33 篇 natl univ singap...
32 篇 yonsei univ
32 篇 shanghai jiao to...
29 篇 univ chinese aca...
29 篇 korea adv inst s...
28 篇 megvii technol p...
28 篇 univ hong kong p...
28 篇 tech univ munich...
27 篇 alibaba grp peop...
26 篇 australian natl ...

作者

68 篇 timofte radu
25 篇 van gool luc
23 篇 zhang lei
21 篇 sun jian
19 篇 radu timofte
17 篇 yang yi
16 篇 tao dacheng
15 篇 loy chen change
14 篇 fan haoqiang
14 篇 wang xinchao
14 篇 liu shuaicheng
14 篇 lee kyoung mu
14 篇 ji rongrong
13 篇 huang feiyue
13 篇 zhang wei
12 篇 li xin
12 篇 liu yang
12 篇 wang kai
12 篇 pan jinshan
12 篇 lei lei

语言

3,855 篇 英文

检索条件"任意字段=2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021"

共 3855 条记录，以下是241-250 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：

Contrastive Learning Improves Model Robustness Under Label Noise

Contrastive Learning Improves Model Robustness Under Label N...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Ghosh, Aritra Lan, Andrew Univ Massachusetts Amherst MA 01003 USA

ISBN: (纸本)9781665448994

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised robust methods;one can simply replace the CCE loss with a loss that is robust to label noise, or re-weight training samples and down-weight those with higher loss values. Recently, another type of method using semi-supervised learning (SSL) has been proposed, which augments these supervised robust methods to exploit (possibly) noisy samples more effectively. Although supervised robust methods perform well across different data types, they have been shown to be inferior to the SSL methods on image classification tasks under label noise. Therefore, it remains to be seen that whether these supervised robust methods can also perform well if they can utilize the unlabeled samples more effectively. In this paper, we show that by initializing supervised robust methods using representations learned through contrastive learning leads to significantly improved performance under label noise. Surprisingly, even the simplest method (training a classifier with the CCE loss) can outperform the state-of-the-art SSL method by more than 50% under high label noise when initialized with contrastive learning. Our implementation will be publicly available at https://***/arghosh/noisy_label_pretrain.

关键词： Training Visualization conferences Training data Semisupervised learning Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Difficulty Estimation with Action Scores for computer vision Tasks

Difficulty Estimation with Action Scores for Computer Vision...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Arriaga, Octavio Palacio, Sebastian Valdenegro-Toro, Matias Univ Bremen Bremen Germany German Res Ctr Artificial Intelligence Kaiserslautern Germany Univ Groningen Groningen Netherlands

ISBN: (纸本)9798350302493

As more machine learning models are now being applied in real world scenarios it has become crucial to evaluate their difficulties and biases. In this paper we present an unsupervised method for calculating a difficulty score based on the accumulated loss per epoch. Our proposed method does not require any modification to the model, neither any external supervision, and it can be easily applied to a wide range of machine learning tasks. We provide results for the tasks of image classification, image segmentation, and object detection. We compare our score against similar metrics and provide theoretical and empirical evidence of their difference. Furthermore, we show applications of our proposed score for detecting incorrect labels, and test for possible biases.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Towards Fair Federated Learning with Zero-Shot Data Augmentation

Towards Fair Federated Learning with Zero-Shot Data Augmenta...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Hao, Weituo El-Khamy, Mostafa Lee, Jungwon Zhang, Jianyi Liang, Kevin J. Chen, Changyou Carin, Lawrence Duke Univ Durham NC 27706 USA Samsung Suwon South Korea SUNY Buffalo Buffalo NY USA

ISBN: (纸本)9781665448994

Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models, while having no access to the client data. Although it is recognized that statistical heterogeneity of the client local data yields slower global model convergence, it is less commonly recognized that it also yields a biased federated global model with a high variance of accuracy across clients. In this work, we aim to provide federated learning schemes with improved fairness. To tackle this challenge, we propose a novel federated learning system that employs zero-shot data augmentation on under-represented data to mitigate statistical heterogeneity, and encourage more uniform accuracy performance across clients in federated networks. We study two variants of this scheme, Fed-ZDAC (federated learning with zero-shot data augmentation at the clients) and Fed-ZDAS (federated learning with zero-shot data augmentation at the server). Empirical results on a suite of datasets demonstrate the effectiveness of our methods on simultaneously improving the test accuracy and fairness.

关键词： computer vision computer aided instruction Distance learning conferences Distributed databases Collaborative work Data models

来源：评论

学校读者我要写书评

暂无评论

Detecting Anomalies in Semantic Segmentation with Prototypes

Detecting Anomalies in Semantic Segmentation with Prototypes

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Fontanel, Dario Cermelli, Fabio Mancini, Massimiliano Caputo, Barbara Politecn Torino Turin Italy Italian Inst Technol Genoa Italy Univ Tubingen Tubingen Germany

ISBN: (纸本)9781665448994

Traditional semantic segmentation methods can recognize at test time only the classes that are present in the training set. This is a significant limitation, especially for semantic segmentation algorithms mounted on intelligent autonomous systems, deployed in realistic settings. Regardless of how many classes the system has seen at training time, it is inevitable that unexpected, unknown objects will appear at test time. The failure in identifying such anomalies may lead to incorrect, even dangerous behaviors of the autonomous agent equipped with such segmentation model when deployed in the real world. Current state of the art of anomaly segmentation uses generative models, exploiting their incapability to reconstruct patterns unseen during training. However, training these models is expensive, and their generated artifacts may create false anomalies. In this paper we take a different route and we propose to address anomaly segmentation through prototype learning. Our intuition is that anomalous pixels are those that are dissimilar to all class prototypes known by the model. We extract class prototypes from the training data in a lightweight manner using a cosine similarity-based classifier. Experiments on Street Hazards show that our approach achieves the new state of the art, with a significant margin over previous works, despite the reduced computational overhead.

关键词： Training Visualization computer vision Computational modeling conferences Semantics Prototypes

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Multi-Task Pretraining Improves Image Aesthetic Assessment

Self-Supervised Multi-Task Pretraining Improves Image Aesthe...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Pfister, Jan Kobs, Konstantin Hotho, Andreas Univ Wurzburg Wurzburg Germany

ISBN: (纸本)9781665448994

Neural networks for Image Aesthetic Assessment are usually initialized with weights of pretrained ImageNet models and then trained using a labeled image aesthetics dataset. We argue that the ImageNet classification task is not well-suited for pretraining, since content based classification is designed to make the model invariant to features that strongly influence the image's aesthetics, e.g. style-based features such as brightness or contrast. We propose to use self-supervised aesthetic-aware pretext tasks that let the network learn aesthetically relevant features, based on the observation that distorting aesthetic images with image filters usually reduces their appeal. To ensure that images are not accidentally improved when filters are applied, we introduce a large dataset comprised of highly aesthetic images as the starting point for the distortions. The network is then trained to rank less distorted images higher than their more distorted counterparts. To exploit effects of multiple different objectives, we also embed this task into a multi-task setting by adding either a self-supervised classification or regression task. In our experiments, we show that our pretraining improves performance over the ImageNet initialization and reduces the number of epochs until convergence by up to 47 %. Additionally, we can match the performance of an ImageNet-initialized model while reducing the labeled training data by 20 %. We make our code, data, and pretrained models available.

关键词： computer vision conferences Computational modeling Neural networks Training data Distortion Data models

来源：评论

学校读者我要写书评

暂无评论

Indirect synthetic attack on thermal face biometric systems via visible-to-thermal spectrum conversion

Indirect synthetic attack on thermal face biometric systems ...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Mallat, Khawla Dugelay, Jean-Luc EURECOM Sophia Antipolis France

ISBN: (纸本)9781665448994

The growing interest in exploring thermal face biometrics is mostly due to the robustness of thermal imagery to face spoofing attacks. However, this robustness lies in the acquisition of thermal properties by the thermal sensor and is limited to presentation attacks. In this paper, we propose a new type of attack on thermal face recognition systems, performed at the post-sensor level. In the visible spectrum, this attack would be carried out by simply injecting a face image of the claimed identity into the communication channel right after the sensor. However, unlike visible face images that are abundantly available on the web, thermal face images are not easy to obtain. Therefore, we propose to generate synthetic thermal attacks by converting visible face images into the thermal spectrum. To perform visible-to-thermal spectrum conversion, we use a cascaded refinement network trained using contextual loss. In a scenario where the attacker has prior knowledge about the spoofing countermeasure of the system, we introduce a new loss computed at the local binary pattern (LBP) maps level to fool an LBP-based spoofing attack detection algorithm. The vulnerability of thermal face biometric systems to the proposed attack is then assessed using two existing baselines of spoofing attack detection. When compared to the challenging presentation attack using silicone masks, the equal error rate has increased from 0.20% to 11.60% and from 2.28% to 58.54% when exposed to the proposed synthetic attack, using the two spoofing attack detection baselines.

关键词： computer vision Error analysis Social networking (online) Face recognition conferences Communication channels Thermal sensors

来源：评论

学校读者我要写书评

暂无评论

Combining Weight Pruning and Knowledge Distillation For CNN Compression

Combining Weight Pruning and Knowledge Distillation For CNN ...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Aghli, Nima Ribeiro, Eraldo Florida Inst Technol 150 W Univ Blvd Melbourne FL 32901 USA

ISBN: (纸本)9781665448994

Complex deep convolutional neural networks such as ResNet require expensive hardware such as powerful GPUs to achieve real-time performance. This problem is critical for applications that run on low-end embedded GPU or CPU systems with limited resources. As a result, model compression for deep neural networks becomes an important research topic. Popular compression methods such as weight pruning remove redundant neurons from the CNN without affecting the network's output accuracy. While these pruning methods work well on simple networks such as VGG or AlexNet, they are not suitable for compressing current state-of-the-art networks such as ResNets because of these networks' complex architectures with dimensionality dependencies. This dependency results in filter pruning breaking the structure of ResNets leading to an untrainable network. In this paper, we first use the weight pruning method only on a selective number of layers in the ResNet architecture to avoid breaking the network structure. Second, we introduce a knowledge distillation architecture and a loss function to compress the untouched layers during the pruning. We test our method on both image-based regression and classification networks for head-pose estimation and image classification. Our compression method reduces the models' size significantly while maintaining the accuracy very close to the baseline model.

关键词： Image coding Neurons Estimation Graphics processing units computer architecture Real-time systems Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Aerial View Object Classification Challenge Results - PBVS 2022

Multi-modal Aerial View Object Classification Challenge Resu...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Low, Spencer Nina, Oliver Sappa, Angel D. Blasch, Erik Brigham Young Univ Provo UT 84602 USA Air Force Res Lab Dayton OH USA ESPOL Polytech Univ Ecuador Comp Vision Ctr Guayaquil Ecuador Air Force Off Sci Res Arlington VA USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

This paper details the results and main findings of the second iteration of the Multi-modal Aerial View Object Classification (MAVOC) challenge. The primary goal of both MAVOC challenges is to inspire research into methods for building recognition models that utilize both synthetic aperture radar (SAR) and electro-optical (EO) imagery. Teams are encouraged to develop multi-modal approaches that incorporate complementary information from both domains. While the 2021 challenge showed a proof of concept that both modalities could be used together, the 2022 challenge focuses on the detailed multi-modal methods. The 2022 challenge uses the same UNIfied COincident Optical and Radar for recognition (UNICORN) dataset and competition format that was used in 2021. Specifically, the challenge focuses on two tasks, (1) SAR classification and (2) SAR + EO classification. The bulk of this document is dedicated to discussing the top performing methods and describing their performance on our blind test set. Notably, all of the top ten teams outperform a Resnet-18 baseline. For SAR classification, the top team showed a 129% improvement over baseline and an 8% average improvement from the 2021 winner. The top team for SAR + EO classification shows a 165% improvement with a 32% average improvement over 2021.

关键词： Training Laser radar Image recognition Radar imaging Optical imaging pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Privacy Leakage of Adversarial Training Models in Federated Learning Systems

Privacy Leakage of Adversarial Training Models in Federated ...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Zhang, Jingyang Chen, Yiran Li, Hai Duke Univ Dept Elect & Comp Engn Durham NC 27706 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, we further reveal this unsettling property of AT by designing a novel privacy attack that is practically applicable to the privacy-sensitive Federated Learning (FL) systems. Using our method, the attacker can exploit AT models in the FL system to accurately reconstruct users' private training images even when the training batch size is large. Code is available at https://***/zjysteven/PrivayAttack_AT_FL.

关键词： Training Deep learning Privacy computer vision conferences Neural networks Collaborative work

来源：评论

学校读者我要写书评

暂无评论

Persistent-Transient Duality in Human Behavior Modeling

Persistent-Transient Duality in Human Behavior Modeling

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Hung Tran Vuong Le Venkatesh, Svetha Truyen Tran Deakin Univ Appl AI Inst Geelong Vic Australia

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We propose to model the persistent-transient duality in human behavior using a parent-child multi-channel neural network, which features a parent persistent channel that manages the global dynamics and children transient channels that are initiated and terminated on-demand to handle detailed interactive actions. The short-lived transient sessions are managed by a proposed Transient Switch. The neural framework is trained to discover the structure of the duality automatically. Our model shows superior performances in human-object interaction motion prediction.

关键词： computer vision Computational modeling conferences Dynamics Neural networks Switches Predictive models

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386页 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：