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

3,310 篇 会议
3 篇 期刊文献

馆藏范围

3,313 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,936 篇 工学
- 1,843 篇 计算机科学与技术...
- 201 篇 软件工程
- 147 篇 机械工程
- 134 篇 光学工程
- 41 篇 生物工程
- 28 篇 信息与通信工程
- 18 篇 电气工程
- 13 篇 控制科学与工程
- 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
360 篇 医学
- 359 篇 临床医学
- 3 篇 基础医学(可授医学...
178 篇 理学
- 137 篇 物理学
- 42 篇 生物学
- 30 篇 数学
- 16 篇 统计学（可授理学、...
- 10 篇 化学
- 3 篇 系统科学
14 篇 管理学
- 7 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 农学
1 篇 经济学

主题

1,738 篇 computer vision
900 篇 training
802 篇 conferences
643 篇 pattern recognit...
482 篇 computational mo...
431 篇 computer archite...
430 篇 task analysis
426 篇 visualization
350 篇 feature extracti...
317 篇 semantics
308 篇 three-dimensiona...
243 篇 neural networks
227 篇 benchmark testin...
222 篇 cameras
183 篇 image segmentati...
177 篇 estimation
168 篇 deep learning
156 篇 measurement
154 篇 object detection
151 篇 data models

机构

40 篇 univ sci & techn...
31 篇 peng cheng lab p...
29 篇 swiss fed inst t...
29 篇 sensetime res pe...
27 篇 university of sc...
27 篇 zhejiang univ pe...
26 篇 univ chinese aca...
26 篇 swiss fed inst t...
25 篇 university of ch...
24 篇 tsinghua univ pe...
24 篇 univ chinese aca...
24 篇 nanyang technol ...
24 篇 sun yat sen univ...
22 篇 peng cheng labor...
20 篇 shanghai ai lab ...
20 篇 korea adv inst s...
19 篇 chinese univ hon...
19 篇 yonsei univ
18 篇 peking univ peop...
18 篇 tsinghua univers...

作者

65 篇 timofte radu
21 篇 loy chen change
18 篇 van gool luc
18 篇 radu timofte
16 篇 zha zheng-jun
14 篇 sun jian
12 篇 fan haoqiang
12 篇 chen wei-ting
12 篇 lei lei
12 篇 qiao yu
11 篇 zheng wei-shi
11 篇 zheng-jun zha
11 篇 liu shuaicheng
11 篇 qi tian
11 篇 luc van gool
11 篇 marcos v. conde
11 篇 liu shuai
11 篇 van de weijer jo...
10 篇 danelljan martin
10 篇 kim seon joo

语言

3,311 篇 英文
2 篇 其他

检索条件"任意字段=2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020"

共 3313 条记录，以下是351-360 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：

CNLL: A Semi-supervised Approach For Continual Noisy Label Learning

CNLL: A Semi-supervised Approach For Continual Noisy Label L...

引用

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

作者： Karim, Nazmul Khalid, Umar Esmaeili, Ashkan Rahnavard, Nazanin Univ Cent Florida Dept Elect & Comp Engn Orlando FL 32816 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

The task of continual learning requires careful design of algorithms that can tackle catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario, seems to exacerbate the situation. While very few studies have addressed the issue of continual learning under noisy labels, long training time and complicated training schemes limit their applications in most cases. In contrast, we propose a simple purification technique to effectively cleanse the online data stream that is both cost-effective and more accurate. After purification, we perform fine-tuning in a semi-supervised fashion that ensures the participation of all available samples. Training in this fashion helps us learn a better representation that results in state-of-the-art (SOTA) performance. Through extensive experimentation on 3 benchmark datasets, MNIST, CIFAR10 and CIFAR100, we show the effectiveness of our proposed approach. We achieve a 24.8% performance gain for CIFAR10 with 20% noise over previous SOTA methods. Our code is publicly available.(1)

关键词： Training computer vision Codes Purification conferences Benchmark testing Performance gain

来源：评论

学校读者我要写书评

暂无评论

Visual Goal-Directed Meta-Imitation Learning

Visual Goal-Directed Meta-Imitation Learning

引用

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

作者： Rivera, Corban G. Handelman, David A. Ratto, Christopher R. Patrone, David Paulhamus, Bart L. Johns Hopkins Univ Intelligent Syst Ctr Appl Phys Lab Laurel MD 20723 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

The goal of meta-learning is to generalize to new tasks and goals as quickly as possible. Ideally, we would like approaches that generalize to new goals and tasks on the first attempt. Requiring a policy to perform on a new task on the first attempt without even a single example trajectory is a zero-shot problem formulation. When tasks are identified by goal images, the tasks can be considered visually goal-directed. In this work, we explore the problem of visual goal-directed zero-shot meta-imitation learning. Inspired by several popular approaches to Meta-RL, we composed several core ideas related to task-embedding and planning by gradient descent to attempt to explore this problem. To evaluate these approaches, we adapted the Meta-world benchmark tasks to create 24 distinct visual goal-directed manipulation tasks. We found that 7 out of 24 tasks could be successfully completed on the first attempt by at least one of the approaches we tested. We demonstrated that goal-directed zero-shot approaches can translate to a physical robot with a demonstration based on Jenga block manipulation tasks using a Kinova Jaco robotic arm.

关键词： Visualization computer vision conferences Benchmark testing Manipulators Trajectory Planning

来源：评论

学校读者我要写书评

暂无评论

Color Invariant Skin Segmentation

Color Invariant Skin Segmentation

引用

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

作者： Xu, Han Sarkar, Abhijit Abbott, A. Lynn Virginia Tech Bradley Dept Elect & Comp Engn Blacksburg VA 24061 USA Virginia Tech Virginia Tech Transportat Inst Blacksburg VA 24061 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

This paper addresses the problem of automatically detecting human skin in images without reliance on color information. A primary motivation of the work has been to achieve results that are consistent across the full range of skin tones, even while using a training dataset that is significantly biased toward lighter skin tones. Previous skin-detection methods have used color cues almost exclusively, and we present a new approach that performs well in the absence of such information. A key aspect of the work is dataset repair through augmentation that is applied strategically during training, with the goal of color invariant feature learning to enhance generalization. We have demonstrated the concept using two architectures, and experimental results show improvements in both precision and recall for most Fitzpatrick skin tones in the benchmark ECU dataset. We further tested the system with the RFW dataset to show that the proposed method performs much more consistently across different ethnicities, thereby reducing the chance of bias based on skin color. To demonstrate the effectiveness of our work, extensive experiments were performed on grayscale images as well as images obtained under unconstrained illumination and with artificial filters.

关键词： Training Representation learning computer vision Sensitivity Image color analysis Lighting Color

来源：评论

学校读者我要写书评

暂无评论

CSG0: Continual Urban Scene Generation with Zero Forgetting

CSG0: Continual Urban Scene Generation with Zero Forgetting

引用

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

作者： Jain, Himalaya Tuan-Hung Vu Perez, Patrick Cord, Matthieu Valeo Ai Paris France Sorbonne Univ Paris France

ISBN: (纸本)9781665487399

With the rapid advances in generative adversarial networks (GANs), the visual quality of synthesised scenes keeps improving, including for complex urban scenes with applications to automated driving. We address in this work a continual scene generation setup in which GANs are trained on a stream of distinct domains;ideally, the learned models should eventually be able to generate new scenes in all seen domains. This setup reflects the real-life scenario where data are continuously acquired in different places at different times. In such a continual setup, we aim for learning with zero forgetting, i.e., with no degradation in synthesis quality over earlier domains due to catastrophic forgetting. To this end, we introduce a novel framework that not only (i) enables seamless knowledge transfer in continual training but also (ii) guarantees zero forgetting with a small overhead cost. While being more memory efficient, thanks to continual learning, our model obtains better synthesis quality as compared against the brute-force solution that trains one full model for each domain. Especially, under extreme low-data regimes, our approach outperforms the brute-force one by a large margin.

关键词： Training Visualization Costs Semantics Memory management Generative adversarial networks pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution with Collapsible Linear Blocks

Efficient Image Super-Resolution with Collapsible Linear Blo...

引用

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

作者： Wang, Li Li, Dong Tian, Lu Shan, Yi Adv Micro Devices Inc Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

In this paper, we propose a simple but effective architecture for fast and accurate single image super-resolution. Unlike other compact image super-resolution methods based on hand-crafted designs, we first apply coarse-grained pruning for network acceleration, and then introduce collapsible linear blocks to recover the representative ability of the pruned network. Specifically, each collapsible linear block has a multi-branch topology during training, and can be equivalently replaced with a single convolution in the inference stage. Such decoupling of the training-time and inference-time architecture is implemented via a structural re-parameterization technique, leading to improved representation without introducing extra computation costs. Additionally, we adopt a two-stage training mechanism with progressively larger patch sizes to facilitate the optimization procedure. We evaluate the proposed method on the NTIRE 2022 Efficient Image Super-Resolution Challenge and achieve a good trade-off between latency and accuracy. Particularly, under the condition of limited inference time (<= 49.42ms) and parameter amount (<= 0.894M), our solution obtains the best fidelity results in terms of PSNR, i.e., 29.05dB and 28.75dB on the DIV2K validation and test sets, respectively.

关键词： Training Costs Network topology Convolution conferences Superresolution computer architecture

来源：评论

学校读者我要写书评

暂无评论

Update Compression for Deep Neural Networks on the Edge

Update Compression for Deep Neural Networks on the Edge

引用

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

作者： Chen, Bo Bakhshi, Ali Batista, Gustavo Ng, Brian Chin, Tat-Jun Univ Adelaide Adelaide SA Australia Univ New South Wales Sydney NSW Australia

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

An increasing number of artificial intelligence (AI) applications involve the execution of deep neural networks (DNNs) on edge devices. Many practical reasons motivate the need to update the DNN model on the edge device post-deployment, such as refining the model, concept drift, or outright change in the learning task. In this paper, we consider the scenario where retraining can be done on the server side based on a copy of the DNN model, with only the necessary data transmitted to the edge to update the deployed model. However, due to bandwidth constraints, we want to minimise the transmission required to achieve the update. We develop a simple approach based on matrix factorisation to compress the model update-this differs from compressing the model itself. The key idea is to preserve existing knowledge in the current model and optimise only small additional parameters for the update which can be used to reconstitute the model on the edge. We compared our method to similar techniques used in federated learning;our method usually requires less than half of the update size of existing methods to achieve the same accuracy.

关键词： Deep learning Neural networks Refining Redundancy Bandwidth Data models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An Empirical study of Data-Free Quantization's Tuning Robustness

An Empirical study of Data-Free Quantization's Tuning Robust...

引用

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

作者： Chen, Hong Wen, Yuxuan Ding, Yifu Yang, Zhen Guo, Yufei Qin, Haotong Beihang Univ Beijing Peoples R China Shanghai Aerosp Elect Technol Inst Shanghai Peoples R China China Aerosp Sci & Ind Corp Acad 2 Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Deep convolutional neural networks are now performing increasingly superior in various fields, while the network parameters are getting massive as the advanced neural networks tend to be deeper. Among various model compression methods, quantization is one of the most potent approaches to compress neural networks by compacting model weights and activations to lower bit-width. The data-free quantization method is also proposed, which is specialized for some privacy and security scenarios and enables quantization without access to real data. In this work, we find that the tuning robustness of existing data-free quantization is flawed, progressing an empirical study and determining some hyperparameter settings that can converge the model stably in the data-free quantization process. Our study aims to evaluate the overall tuning robustness of the current data-free quantization system, which is existing methods are significantly affected by parameter fluctuations in tuning. We also expect data-free quantification methods with tuning robustness to appear in the future.

关键词： Data privacy Quantization (signal) Fluctuations conferences Neural networks Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image recognition

Incremental Meta-Learning via Episodic Replay Distillation f...

引用

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

作者： Wang, Kai Liu, Xialei Bagdanov, Andy Herranz, Luis Jui, Shangling van de Weijer, Joost Comp Vis Ctr Barcelona Spain Nankai Univ Tianjin Peoples R China Univ Florence MICC Florence Italy Huawei Kirin Solut Shanghai Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

In this paper we consider the problem of incremental meta-learning in which classes are presented incrementally in discrete tasks. We propose Episodic Replay Distillation (ERD), that mixes classes from the current task with exemplars from previous tasks when sampling episodes for meta-learning. To allow the training to benefit from a large as possible variety of classes, which leads to more generalizable feature representations, we propose the cross-task meta loss. Furthermore, we propose episodic replay distillation that also exploits exemplars for improved knowledge distillation. Experiments on four datasets demonstrate that ERD surpasses the state-of-the-art. In particular, on the more challenging one-shot, long task sequence scenarios, we reduce the gap between Incremental Meta-Learning and the joint-training upper bound from 3.5% / 10.1% / 13.4% / 11.7% with the current state-of-the-art to 2.6% / 2.9% / 5.0% / 0.2% with our method on Tiered-ImageNet / Mini-ImageNet / CIFAR100 / CUB, respectively.

关键词： Training computer vision Image recognition Upper bound conferences pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimensional vision Transformer Compression via Dependency Guided Gaussian Process Search

Multi-Dimensional Vision Transformer Compression via Depende...

引用

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

作者： Hou, Zejiang Kung, Sun-Yuan Princeton Univ Princeton NJ 08544 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

vision transformers (ViT) have recently attracted considerable attentions, but the huge computational cost remains an issue for practical deployment. Previous ViT pruning methods tend to prune the model along one dimension solely, which may suffer from excessive reduction and lead to sub-optimal model quality. In contrast, we advocate a multi-dimensional ViT compression paradigm, and propose to harness the redundancy reduction from attention head, neuron and sequence dimensions jointly. Firstly, we propose a statistical dependence based pruning criterion that is generalizable to different dimensions for identifying the deleterious components. Moreover, we cast the multi-dimensional ViT compression as an optimization problem, objective of which is to learn an optimal pruning policy across the three dimensions while maximizing the compressed model's accuracy under a computational budget. The problem is solved by an adapted Gaussian process search with expected improvement. Experimental results show that our method effectively reduces the computational cost of various ViT models. For example, our method reduces 40% FLOPs without top-1 accuracy loss for DeiT and T2T-ViT models on the ImageNet dataset, outperforming previous state-of-the-art ViT pruning methods.

关键词： Adaptation models Image coding Head Computational modeling Neurons Gaussian processes Transformers

来源：评论

学校读者我要写书评

暂无评论

SaR: Self-adaptive Refinement on Pseudo Labels for Multiclass-Imbalanced Semi-supervised Learning

SaR: Self-adaptive Refinement on Pseudo Labels for Multiclas...

引用

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

作者： Lai, Zhengfeng Wang, Chao Cheung, Sen-ching Chuah, Chen-Nee Univ Calif Davis Davis CA 95616 USA Southern Univ Sci & Technol Shenzhen Peoples R China Univ Kentucky Lexington KY 40506 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Class-imbalanced datasets can severely deteriorate the performance of semi-supervised learning (SSL). This is due to the confirmation bias especially when the pseudo labels are highly biased towards the majority classes. Traditional resampling or reweighting techniques may not be directly applicable when the unlabeled data distribution is unknown. Inspired by the threshold-moving method that performs well in supervised learning-based binary classification tasks, we provide a simple yet effective scheme to address the multiclass imbalance issue of SSL. This scheme, named SaR, is a Self-adaptive Refinement of soft labels before generating pseudo labels. The pseudo labels generated post-SaR will be less biased, resulting in higher quality data for training the classifier. We show that SaR can consistently improve recent consistency-based SSL algorithms on various image classification problems across different imbalanced ratios. We also show that SaR is robust to the situations where unlabeled data have different distributions as labeled data. Hence, SaR does not rely on the assumptions that unlabeled data share the same distribution as the labeled data.

关键词： Training computer vision conferences Semisupervised learning pattern recognition Classification algorithms Task analysis

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 << < 32 33 34 35 36 37 38 39 40 41 > >>

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：