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

83 篇 期刊文献
44 篇 会议

馆藏范围

127 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

126 篇 工学
- 83 篇 计算机科学与技术...
- 48 篇 电气工程
- 15 篇 测绘科学与技术
- 14 篇 软件工程
- 13 篇 控制科学与工程
- 11 篇 电子科学与技术（可...
- 9 篇 信息与通信工程
- 9 篇 环境科学与工程（可...
- 5 篇 仪器科学与技术
- 4 篇 机械工程
- 4 篇 材料科学与工程（可...
- 1 篇 冶金工程
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 纺织科学与工程
31 篇 医学
- 31 篇 临床医学
- 3 篇 基础医学(可授医学...
28 篇 理学
- 14 篇 地球物理学
- 9 篇 物理学
- 7 篇 化学
- 3 篇 地理学
- 3 篇 生物学
- 2 篇 数学
- 2 篇 统计学（可授理学、...
4 篇 管理学
- 3 篇 管理科学与工程(可...
- 1 篇 图书情报与档案管...

主题

127 篇 few-shot object ...
23 篇 object detection
16 篇 few-shot learnin...
12 篇 transfer learnin...
10 篇 remote sensing i...
9 篇 meta-learning
7 篇 contrastive lear...
6 篇 task analysis
6 篇 feature extracti...
6 篇 detectors
5 篇 deep learning
5 篇 metric learning
5 篇 training
4 篇 data augmentatio...
3 篇 transformer
3 篇 proposals
3 篇 feature enhancem...
3 篇 prototypes
3 篇 fine-tuning
3 篇 meta learning

机构

3 篇 northwestern pol...
3 篇 univ chinese aca...
3 篇 chinese acad sci...
2 篇 xidian univ sch ...
2 篇 ningbo univ fac ...
2 篇 beijing univ tec...
2 篇 univ chinese aca...
2 篇 natl engn lab cr...
2 篇 beijing inst rem...
2 篇 xidian univ guan...
2 篇 tongji univ coll...
2 篇 beihang univ sta...
2 篇 northwestern pol...
2 篇 fudan univ sch d...
2 篇 wuhan inst techn...
2 篇 nanjing univ pos...
2 篇 nanjing univ sci...
2 篇 beijing key lab ...
2 篇 univ elect sci &...
2 篇 purple mt labs m...

作者

3 篇 wang jian
3 篇 cheng gong
3 篇 han junwei
3 篇 zhao lei
3 篇 wang chen
2 篇 shi hongbo
2 篇 wang lei
2 篇 zhang yanan
2 篇 tao yang
2 篇 wang wenjian
2 篇 cai youpeng
2 篇 zhu songhao
2 篇 le jeune pierre
2 篇 tang chi-keung
2 篇 liu weijie
2 篇 fan qi
2 篇 fu yanwei
2 篇 tan shuai
2 篇 tai yu-wing
2 篇 xu chengming

语言

126 篇 英文
1 篇 其他

检索条件"主题词=Few-Shot Object Detection"

共 127 条记录，以下是81-90 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：

HOSENet: Higher-Order Semantic Enhancement for few-shot object detection 3rd

HOSENet: Higher-Order Semantic Enhancement for Few-Shot Obje...

引用

3rd Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Zhang, Lingli Chen, Ke-Jia Zhou, Xiaomeng Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing Peoples R China Nanjing Univ Posts & Telecommun Jiangsu Key Lab Big Data Secur & Intelligent Proc Nanjing Peoples R China Nanjing Univ Posts & Telecommun Sch Commun & Informat Engn Nanjing Peoples R China

ISBN: (纸本)9783030606381;9783030606398

few-shot object detection is to detect objects of novel categories from only a few annotated examples and has recently attracted attention. Existing methods focus on designing new training strategies on a widely used object detection network, while ignoring the importance of network representation ability for this problem. This paper proposes a novel network model named HOSENet, which introduces a higher-order semantic enhancement module (e.g. second-order pooling) in the forward process of the network. The entire network is first trained with base class data and then fine-tuned by support images to detect objects of novel classes. Experiments on PASCAL VOC and MS COCO show that the detection precision of our method in novel classes is far superior to other competitive methods without compromising the detection precision in base classes.

关键词： few-shot object detection Semantic enhancement Second-order pooling

来源：评论

学校读者我要写书评

暂无评论

A Closer Look at few-shot object detection 6th

A Closer Look at Few-Shot Object Detection

引用

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Liu, Yuhao Dong, Le He, Tengyang Univ Elect Sci & Technol China Dept Comp Sci & Technol Chengdu Peoples R China

ISBN: (纸本)9789819985425;9789819985432

few-shot object detection, which aims to detect unseen classes in data-scarce scenarios, remains a challenging task. Most existing works adopt Faster RCNN as the basic framework and employ fine-tuning paradigm to tackle this problem. However, the intrinsic concept drift in the Region Proposal Network and the rejection of false positive region proposals hinder model performance. In this paper, we introduce a simple and effective task adapter in RPN, which decouples it from the backbone network to obtain category-agnostic knowledge. In the last two layers of the task adapter, we use large-kernel spatially separable convolution to adaptively detect objects at different scales. In addition, We design an offline structural reparameterization approach to better initialize box classifiers by constructing an augmented dataset to learn initial novel prototypes and explicitly incorporating priors from base training in extremely low-shot scenarios. Extensive experiments on various benchmarks have demonstrated that our proposed method is significantly superior to other methods and is comparative with state-of-the-art performance.

关键词： few-shot learning object detection few-shot object detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based few-shot object detection with Enhanced Fine-Tuning Stability

Transformer-Based Few-Shot Object Detection with Enhanced Fi...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chen, Zuyu Li, Ya-Li Wang, Shengjin Tsinghua Univ Dept Elect Engn Beijing Peoples R China Beijing Natl Res Ctr Informat Sci & Technol BNRis Beijing Peoples R China

ISBN: (纸本)9798350359329;9798350359312

few-shot object detection (FSOD) aims at detecting unseen classes with limited annotated novel examples. while the fine-tuning paradigm has been proven effective for FSOD, most existing approaches are based on Faster R-CNN framework, neglecting exploration of advanced frameworks such as DETR. In this paper, we propose a transformer-based few-shot object detection method. To address the instability issue in few-shot fine-tuning of DETR, we propose a simple yet effective method to enhance the fine-tuning stability from two perspectives: 1) an enhanced initialization method for classification layer, hollow initialization. 2) Category-Level Dropout (CLD), to mitigate effect of missing annotations by controlling gradient backpropagation of classifier. Comprehensive experimental results on MS COCO show that our method significantly improves the baseline and achieves very promising performance.

关键词： few-shot object detection transformer-Based Fine-tuning

来源：评论

学校读者我要写书评

暂无评论

ADVANCING CONTROLLABLE DIFFUSION MODEL FOR few-shot object detection IN OPTICAL REMOTE SENSING IMAGERY

ADVANCING CONTROLLABLE DIFFUSION MODEL FOR FEW-SHOT OBJECT D...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Zhang, Tong Zhuang, Yin Zhang, Xinyi Wang, Guanqun Chen, He Bi, Fukun Beijing Inst Technol Natl Key Lab Sci & Technol Space Born Intelligent Beijing 100081 Peoples R China Peking Univ Beijing 100871 Peoples R China North China Univ Technol Beijing 100144 Peoples R China

ISBN: (纸本)9798350360332;9798350360325

few-shot object detection (FSOD) from optical remote sensing imagery has to detect rare objects given only a few annotated bounding boxes. The limited training data is hard to represent the data distribution of realistic remote sensing scenes, restricting the performance of FSOD. Recently, learning conditional controls for text-to-image diffusion model has achieved great progress, which is capable of precisely generating the controllable yet imaginational images by text prompt and spatially localized input conditions. Accordingly, in this work, we aim to explore the potential of diffusion model and propose a solution for few-shot object detection by controllable data generation. Firstly, draw upon a few annotated objects, their bounding boxes and categories are respectively used as the spatial conditions and text prompts, then employ them into large text-to-image diffusion models for controlled image generation. Secondly, based the generated images, in order to adapt to the scale and orientation variances of remote sensing objects, a data transformation is devised for boosting the robustness of model training. Finally, some experiments were conducted on public remote sensing dataset DIOR, and the results proved its effectiveness.

关键词： Diffusion model few-shot object detection optical remote sensing imagery stable diffusion.

来源：评论

学校读者我要写书评

暂无评论

Proposal-level Correction Guided by CLIP for few-shot object detection

Proposal-level Correction Guided by CLIP for Few-shot Object...

引用

2024 Conference on Visual Communications and Image Processing

作者： Wang, Ruihang Zhao, Taijin Mei, Hefei Qiu, Heqian Wang, Lanxiao Li, Hongliang Univ Elect Sci & Technol China Chengdu Peoples R China

ISBN: (纸本)9798331529543;9798331529550

few-shot object detection aims at detecting previously unseen objects given only a few annotated samples. Most existing approaches treat the model obtained from the base training stage with abundant data as a container of prior knowledge that can be transferred to novel objects. Knowledge with similar properties is also contained in Contrastive Language-Image Pretraining (CLIP). In this paper, we utilize this external prior knowledge to generate proposal-level classification scores to improve the detection results. We notice that these scores can hardly reflect the quality of proposal localization, so we combine them with the ones from a conventional detector to obtain the ability to distinguish the background. Moreover, we propose a new score fusion module with regularization to alleviate the ambiguity of detection results generated by a trivial element-wise multiplication fusion method. To further improve the quality of classification scores in our proposed branch, we add learnable prompts to mitigate the inaccurate classification problem we observe. We conduct extensive experiments on the PASCAL VOC dataset and demonstrate the effectiveness of our approach.

关键词： few-shot object detection CLIP prompt learning proposal-level correction

来源：评论

学校读者我要写书评

暂无评论

Delve into Cosine: few-shot object detection via Adaptive Norm-cutting Scale

Delve into Cosine: Few-shot Object Detection via Adaptive No...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhang, Yanan Jin, Yifan Wang, Rui Liu, Lixiang Univ Chinese Acad Sci Chinese Acad Sci Inst Software Beijing 100190 Peoples R China

ISBN: (纸本)9798350359329;9798350359312

In this paper, we provide an analysis of the existing two-stage representation learning framework for the few-shot object detection from the perspective of normalization in the latent space, which is achieved by delving into cosine, thereby exploring the intrinsic reason behind its promotion of the model performance. Accordingly, the motivating experiments demonstrate that the cosine-similarity-based classifier enhances performance by alleviating the model's bias towards the background class. However, the previously fixed scale applied in the classifier still leads to an overestimation of the probability that a novel instance belongs to the background class, thereby retaining the model's bias towards the background. To address this issue, we establish the adaptive norm-cutting scale for instances that are predicted as the background instances, utilizing a learnable parameter to generate an appropriate scale. This optimization leverages our exploration, resulting in an improved few-shot object detection model. Experimental results validate the effectiveness of our approach.

关键词： few-shot object detection Background Cosine Similarity

来源：评论

学校读者我要写书评

暂无评论

MULTI-SCALE CONTEXT-AWARE R-CNN FOR few-shot object detection IN REMOTE SENSING IMAGES

MULTI-SCALE CONTEXT-AWARE R-CNN FOR FEW-SHOT OBJECT DETECTIO...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Su, Haozheng You, Yanan Meng, Gang Beijing Univ Posts & Telecommun Sch Artificial Intelligence Beijing Peoples R China Beijing Inst Remote Sensing Informat Beijing Peoples R China

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

In the field of remote sensing image object detection, the popular CNN-based methods need a large-scale and diverse dataset that is costly, and have limited generalization abilities for new categories. The few-shot object detection can be driven using only a few annotated samples. Existing few-shot detection methods are mainly designed for natural images, which ignore multi-scale objects and complex environments in remote sensing images. To tackle these challenges, we propose a two-stage multi-scale method based on context mechanism. Guided by the context-aware module, the multi-scale contextual information around the object is effectively extract and adaptively is combined into the ROI features to enhance the classification ability of the detector, which can reduce the classification confusion. Comparative experiments on public remote sensing image dataset RSOD show the effectiveness of our method.

关键词： few-shot object detection multi-scale context-aware remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Hierarchical few-shot object detection: Problem, Benchmark and Method 22

Hierarchical Few-Shot Object Detection: Problem, Benchmark a...

引用

30th ACM International Conference on Multimedia (MM)

作者： Zhang, Lu Wang, Yang Zhou, Jiaogen Zhang, Chenbo Zhang, Yinglu Guan, Jihong Bian, Yatao Zhou, Shuigeng Fudan Univ Shanghai Peoples R China Tongji Univ Shanghai Peoples R China Huaiyin Normal Univ Sch Urban & Environm Sci Huaian Peoples R China Tencent AI Lab Shenzhen Peoples R China

ISBN: (纸本)9781450392037

few-shot object detection (FSOD) is to detect objects with a few examples. However, existing FSOD methods do not consider hierarchical fine-grained category structures of objects that exist widely in real life. For example, animals are taxonomically classified into orders, families, genera and species etc. In this paper, we propose and solve a new problem called hierarchical few-shot object detection (Hi-FSOD), which aims to detect objects with hierarchical categories in the FSOD paradigm. To this end, on the one hand, we build the first large-scale and high-quality Hi-FSOD benchmark dataset HiFSOD-Bird, which contains 176,350 wild-bird images falling to 1,432 categories. All the categories are organized into a 4-level taxonomy, consisting of 32 orders, 132 families, 572 genera and 1,432 species. On the other hand, we propose the first Hi-FSOD method HiCLPL, where a hierarchical contrastive learning approach is developed to constrain the feature space so that the feature distribution of objects is consistent with the hierarchical taxonomy and the model's generalization power is strengthened. Meanwhile, a probabilistic loss is designed to enable the child nodes to correct the classification errors of their parent nodes in the taxonomy. Extensive experiments on the benchmark dataset HiFSOD-Bird show that our method HiCLPL outperforms the existing FSOD methods.

关键词： few-shot object detection hierarchical few-shot object detection Benchmark hierarchical classification

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Prototype Conditional few-shot object detection 21st

Self-supervised Prototype Conditional Few-Shot Object Detect...

引用

21st International Conference on Image Analysis and Processing (ICIAP)

作者： Kobayashi, Daisuke Toshiba Co Ltd Corp Res & Dev Ctr Kawasaki Kanagawa Japan

ISBN: (纸本)9783031064302;9783031064296

Traditional deep learning-based object detection methods require a large amount of annotation for training, and creating such a dataset is expensive. few-shot object detection which detects a new category of objects with a small amount of data is a difficult task. Many previous methods have been applied to detect new categories with few data by fine-tuning. However, fine-tuning methods cannot be sufficiently adapted quickly to new environments because of time-consuming training. In this study, we develop methods that can be adapted to new categories without fine-tuning. A prototype conditional detection module built on prototypes for each category is intended to be conditioned and detected by prototypes. Moreover, a self-supervised conditional detection module improves the representational capability for detecting new categories by a self-supervised task that uses embeddings outside the annotation region to detect the same regions before and after image transformation. The results of extensive experiments on the PASCAL VOC and MS COCO show the effectiveness of the proposed method.

关键词： few-shot object detection few-shot learning object detection

来源：评论

学校读者我要写书评

暂无评论

Prototype Relation Embedding and Contrastive Learning for Improved few-shot object detection in Sonar Images 11

Prototype Relation Embedding and Contrastive Learning for Im...

引用

11th Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2023

作者： Zhou, Xin Zhou, Zihan Tian, Kun School of Information Science and Technology Dalian Maritime University Liaoning Dalian China

ISBN: (纸本)9798350333664

While recent advancements have significantly elevated the performance of object detection in sonar images, the performance of object detectors experiences a steep decline when trained with a limited number of samples. few-shot object detection (FSOD) in sonar images remains a challenge. In this paper, we propose a novel method based on prototype relation embedding and contrastive learning for few-shot object detection named SRE-Net for sonar images. In the SRE-Net framework, prototype relation embedding network is employed to enhance class prototype representations, facilitating improved region proposal generation by utilizing weighted class prototypes computed from query images. Furthermore, the introduction of a support-guided detection head enables the model to exploit the associative information between query and support images, thereby strengthening inter-object relationships. Meanwhile, a contrastive head is introduced to enhance feature representations, reducing intra-class variations while preserving inter-class differences. Finally, we compare SRE-Net with state-of-the-art few-shot object detection methods on optical and sonar image datasets. The results show that our model demonstrates outstanding detection capability across various evaluation scenarios. © 2023 IEEE.

关键词： contrastive learning few-shot object detection prototype-CNN sonar image

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13页 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：