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

23,135 篇 会议
91 篇 期刊文献
15 册 图书

馆藏范围

23,240 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,631 篇 工学
- 11,162 篇 计算机科学与技术...
- 3,337 篇 软件工程
- 2,414 篇 机械工程
- 1,662 篇 光学工程
- 1,204 篇 电气工程
- 973 篇 控制科学与工程
- 738 篇 信息与通信工程
- 381 篇 仪器科学与技术
- 322 篇 生物工程
- 239 篇 生物医学工程（可授...
- 188 篇 电子科学与技术（可...
- 109 篇 化学工程与技术
- 104 篇 安全科学与工程
- 99 篇 测绘科学与技术
- 85 篇 建筑学
- 82 篇 土木工程
- 82 篇 交通运输工程
- 56 篇 力学（可授工学、理...
3,696 篇 医学
- 3,684 篇 临床医学
- 76 篇 基础医学(可授医学...
3,137 篇 理学
- 1,880 篇 物理学
- 1,604 篇 数学
- 547 篇 统计学（可授理学、...
- 466 篇 生物学
- 243 篇 系统科学
- 107 篇 化学
491 篇 管理学
- 290 篇 图书情报与档案管...
- 212 篇 管理科学与工程(可...
- 74 篇 工商管理
252 篇 艺术学
- 251 篇 设计学（可授艺术学...
58 篇 法学
38 篇 农学
25 篇 教育学
19 篇 经济学
10 篇 军事学
3 篇 文学

主题

10,396 篇 computer vision
3,893 篇 pattern recognit...
3,101 篇 training
2,104 篇 computational mo...
1,898 篇 visualization
1,800 篇 cameras
1,487 篇 feature extracti...
1,475 篇 three-dimensiona...
1,464 篇 shape
1,447 篇 image segmentati...
1,287 篇 robustness
1,234 篇 computer archite...
1,213 篇 semantics
1,112 篇 benchmark testin...
1,111 篇 conferences
1,104 篇 layout
1,093 篇 object detection
1,085 篇 computer science
1,026 篇 codes
907 篇 face recognition

机构

137 篇 univ sci & techn...
124 篇 univ chinese aca...
121 篇 chinese univ hon...
108 篇 tsinghua univers...
108 篇 carnegie mellon ...
105 篇 microsoft resear...
97 篇 zhejiang univ pe...
91 篇 swiss fed inst t...
85 篇 university of sc...
84 篇 zhejiang univers...
81 篇 shanghai ai lab ...
79 篇 university of ch...
75 篇 shanghai jiao to...
69 篇 microsoft res as...
68 篇 alibaba grp peop...
66 篇 adobe research
65 篇 national laborat...
64 篇 peking univ peop...
61 篇 univ oxford oxfo...
59 篇 peng cheng labor...

作者

80 篇 van gool luc
71 篇 timofte radu
65 篇 zhang lei
43 篇 luc van gool
40 篇 yang yi
37 篇 loy chen change
34 篇 li stan z.
33 篇 liu yang
33 篇 xiaoou tang
33 篇 murino vittorio
33 篇 chen chen
33 篇 qi tian
33 篇 li fei-fei
32 篇 tian qi
32 篇 sun jian
30 篇 ying shan
30 篇 pascal fua
29 篇 darrell trevor
28 篇 li xin
28 篇 hanqing lu

语言

23,162 篇 英文
52 篇 其他
20 篇 中文
5 篇 土耳其文
2 篇 日文

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

共 23241 条记录，以下是301-310 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：

MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning

MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-T...

引用

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

作者： Agiza, Ahmed Neseem, Marina Reda, Sherief Brown Univ Providence RI 02912 USA

ISBN: (纸本)9798350353006

Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning. Consequently, parameter-efficient fine-tuning methods have emerged as a promising way to adapt pre-trained models to different tasks while training only a minimal number of parameters. While most of these methods are designed for single-task adaptation, parameter-efficient training in Multi-Task Learning (MTL) architectures is still unexplored. In this paper, we introduce MTLoRA, a novel framework for parameter-efficient training of MTL models. MTLoRA employs Task-Agnostic and Task-Specific Low-Rank Adaptation modules, which effectively disentangle the parameter space in MTL fine-tuning, thereby enabling the model to adeptly handle both task specialization and interaction within MTL contexts. We applied MTLoRA to hierarchical-transformer-based MTL architectures, adapting them to multiple downstream dense prediction tasks. Our extensive experiments on the PASCAL dataset show that MTLoRA achieves higher accuracy on downstream tasks compared to fully fine-tuning the MTL model while reducing the number of trainable parameters by 3.6x. Furthermore, MTLoRA establishes a Pareto-optimal trade-off between the number of trainable parameters and the accuracy of the downstream tasks, outperforming current state-of-the-art parameter-efficient training methods in both accuracy and efficiency. Our code is publicly available.(1)

关键词： efficient multi-task learning hierarchical transformers LoRA low-rank adapatation multi-task learning parameter-efficient training PEFT vision transformers

来源：评论

学校读者我要写书评

暂无评论

MAPLM: A Real-World Large-Scale vision-Language Benchmark for Map and Traffic Scene Understanding

MAPLM: A Real-World Large-Scale Vision-Language Benchmark fo...

引用

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

作者： Cao, Xu Zhou, Tong Ma, Yunsheng Ye, Wenqian Cui, Can Tang, Kun Cao, Zhipeng Liang, Kaizhao Wang, Ziran Rehg, James M. Zheng, Chao Tencent T Lab Palo Alto CA 94306 USA Univ Illinois Champaign IL USA Purdue Univ W Lafayette IN USA Univ Virginia Charlottesville VA USA SambaNova Syst Inc Palo Alto CA USA

ISBN: (纸本)9798350353006

vision-language generative AI has demonstrated remarkable promise for empowering cross-modal scene understanding of autonomous driving and high-definition (HD) map systems. However, current benchmark datasets lack multi-modal point cloud, image, and language data pairs. Recent approaches utilize visual instruction learning and cross-modal prompt engineering to expand vision-language models into this domain. In this paper, we propose a new vision-language benchmark that can be used to finetune traffic and HD map domain-specific foundation models. Specifically, we annotate and leverage large-scale, broad-coverage traffic and map data extracted from huge HD map annotations, and use CLIP and LLaMA-2 / Vicuna to finetune a baseline model with instruction-following data. Our experimental results across various algorithms reveal that while visual instruction-tuning large language models (LLMs) can effectively learn meaningful representations from MAPLM-QA, there remains significant room for further advancements. To facilitate applying LLMs and multi-modal data into self-driving research, we will release our visual-language QA data, and the baseline models at ***/LLVM-AD/MAPLM.

关键词： High-definition (HD) Map Large Language Model Multimodal Learning vision-Language Model Visual Question Answering

来源：评论

学校读者我要写书评

暂无评论

DiCo-NeRF: Difference of Cosine Similarity for Neural Rendering of Fisheye Driving Scenes

DiCo-NeRF: Difference of Cosine Similarity for Neural Render...

引用

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

作者： Choi, Jiho Hwang, Gyutae Lee, Sang Jun Jeonbuk Natl Univ Jeonju South Korea

ISBN: (纸本)9798350365474

Neural radiance fields have emerged in the field of autonomous driving, which contributes to improve perception of the complex 3D environment through the reconstruction of geometry and appearance. Moving objects and sky for outdoor environment is challenging to optimize the NeRF model. Previous work addresses these challenges through preprocessing such as masking;however, the masking process requires additional ground-truth data and a segmentation network. We propose DiCo-NeRF, an approach for driving scenes by leveraging cosine similarity map differences of vision-language aligned model. DiCo-NeRF investigates the correlation between rendered patches and pre-defined text and adjusts the loss of challenging patches, such as moving objects and the sky. Our neural radiance field utilizes embedding vectors from a pre-trained CLIP to obtain the cosine similarity maps. We introduce SimLoss, a loss function aimed at regulating the color field of NeRF based on the quantified distribution differences between ground-truth and rendered similarity maps. Unlike previous NeRF models that used driving datasets, our approach does not require additional input, such as sensor data, to the model. Experimental results demonstrate that the incorporation of language semantic cues improves the performance of the novel view synthesis task, particularly in complex driving environments. We conducted experiments that included fisheye driving scenes from the KITTI360 and real-world datasets. Our code is available at https://***/ziiho08/DiCoNeRF.

关键词： Autonomous driving Fisheye camera Neural Radiance Fields vision-Language models

来源：评论

学校读者我要写书评

暂无评论

Leveraging vision-Language Models for Improving Domain Generalization in Image Classification

Leveraging Vision-Language Models for Improving Domain Gener...

引用

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

作者： Addepalli, Sravanti Asokan, Ashish Ramayee Sharma, Lakshay Babu, R. Venkatesh Indian Inst Sci Vision & AI Lab Bangalore Karnataka India

ISBN: (纸本)9798350353006

vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. However, in several cases, their expensive training and data collection/curation costs do not justify the end application. This motivates a vendor-client paradigm, where a vendor trains a large-scale VLM and grants only input-output access to clients on a pay-per-query basis in a black-box setting. The client aims to minimize inference cost by distilling the VLM to a student model using the limited available task-specific data, and further deploying this student model in the downstream application. While naive distillation largely improves the In-Domain (ID) accuracy of the student, it fails to transfer the superior out-of-distribution (OOD) generalization of the VLM teacher using the limited available labeled images. To mitigate this, we propose vision-Language to vision - Align, Distill, Predict (VL2V-ADiP), which first aligns the vision and language modalities of the teacher model with the vision modality of a pre-trained student model, and further distills the aligned VLM representations to the student. This maximally retains the pre-trained features of the student, while also incorporating the rich representations of the VLM image encoder and the superior generalization of the text embeddings. The proposed approach achieves state-of-the-art results on the standard Domain Generalization benchmarks in a black-box teacher setting as well as a white-box setting where the weights of the VLM are accessible. Project page: http://***/VL2V-ADiP/

关键词： CLIP Distillation Domain Generalization OOD Generalization vision-language models

来源：评论

学校读者我要写书评

暂无评论

Beyond Image Super-Resolution for Image recognition with Task-Driven Perceptual Loss

Beyond Image Super-Resolution for Image Recognition with Tas...

引用

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

作者： Kim, Jaeha Oh, Junghun Lee, Kyoung Mu Seoul Natl Univ Dept ECE Seoul South Korea Seoul Natl Univ ASRI Seoul South Korea Seoul Natl Univ IPAI Seoul South Korea

ISBN: (纸本)9798350353013;9798350353006

In real-world scenarios, image recognition tasks, such as semantic segmentation and object detection, often pose greater challenges due to the lack of information available within low-resolution (LR) content. Image super-resolution (SR) is one of the promising solutions for addressing the challenges. However, due to the ill-posed property of SR, it is challenging for typical SR methods to restore task-relevant high-frequency contents, which may dilute the advantage of utilizing the SR method. Therefore, in this paper, we propose Super-Resolution for Image recognition (SR4IR) that effectively guides the generation of SR images beneficial to achieving satisfactory image recognition performance when processing LR images. The critical component of our SR4IR is the task-driven perceptual (TDP) loss that enables the SR network to acquire task-specific knowledge from a network tailored for a specific task. Moreover, we propose a cross-quality patch mix and an alternate training framework that significantly enhances the efficacy of the TDP loss by addressing potential problems when employing the TDP loss. Through extensive experiments, we demonstrate that our SR4IR achieves outstanding task performance by generating SR images useful for a specific image recognition task, including semantic segmentation, object detection, and image classification. The implementation code is available at https://***/JaehaKim97/SR4IR.

关键词： Low-level vision Perceptual loss Super-resolution Task-aware restoration

来源：评论

学校读者我要写书评

暂无评论

Differentiable Shadow Mapping for Efficient Inverse Graphics

Differentiable Shadow Mapping for Efficient Inverse Graphics

引用

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

作者： Worchel, Markus Alexa, Marc TU Berlin Berlin Germany

ISBN: (纸本)9798350301298

We show how shadows can be efficiently generated in differentiable rendering of triangle meshes. Our central observation is that pre-filtered shadow mapping, a technique for approximating shadows based on rendering from the perspective of a light, can be combined with existing differentiable rasterizers to yield differentiable visibility information. We demonstrate at several inverse graphics problems that differentiable shadow maps are orders of magnitude faster than differentiable light transport simulation with similar accuracy - while differentiable rasterization without shadows often fails to converge.

关键词： vision + graphics

来源：评论

学校读者我要写书评

暂无评论

Sat2Cap: Mapping Fine-Grained Textual Descriptions from Satellite Images

Sat2Cap: Mapping Fine-Grained Textual Descriptions from Sate...

引用

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

作者： Dhakal, Aayush Ahmad, Adeel Khanal, Subash Sastry, Srikumar Kerner, Hannah Jacobs, Nathan Washington Univ St Louis MO 63110 USA Taylor Geospatial Inst St Louis MO USA Arizona State Univ Tempe AZ 85287 USA

ISBN: (纸本)9798350365474

We propose a weakly supervised approach for creating maps using free-form textual descriptions. We refer to this work of creating textual maps as zero-shot mapping. Prior works have approached mapping tasks by developing models that predict a fixed set of attributes using overhead imagery. However, these models are very restrictive as they can only solve highly specific tasks for which they were trained. Mapping text, on the other hand, allows us to solve a large variety of mapping problems with minimal restrictions. To achieve this, we train a contrastive learning framework called Sat2Cap on a new large-scale dataset with 6.1M pairs of overhead and ground-level images. For a given location and overhead image, our model predicts the expected CLIP embeddings of the ground-level scenery. The predicted CLIP embeddings are then used to learn about the textual space associated with that location. Sat2Cap is also conditioned on date-time information, allowing it to model temporally varying concepts over a location. Our experimental results demonstrate that our models successfully capture ground-level concepts and allow large-scale mapping of fine-grained textual queries. Our approach does not require any text-labeled data, making the training easily scalable. The code, dataset, and models will be made publicly available.

关键词： Contrastive Learning Text-based Mapping vision-Language Model

来源：评论

学校读者我要写书评

暂无评论

Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions

Improved Zero-Shot Classification by Adapting VLMs with Text...

引用

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

作者： Saha, Oindrila Van Horn, Grant Maji, Subhransu Univ Massachusetts Amherst MA 01003 USA

ISBN: (纸本)9798350353006

The zero-shot performance of existing vision-language models (VLMs) such as CLIP [29] is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources of information-descriptions of categories generated by large language models (LLMs) and abundant, fine- grained image classification datasets-to improve the zero-shot classification performance of VLMs across finegrained domains. On the technical side, we develop methods to train VLMs with this "bag-level" image-text supervision. We find that simply using these attributes at test-time does not improve performance, but our training strategy, for example, on the iNaturalist [41] dataset, leads to an average improvement of 4-5% in zero-shot classification accuracy for novel categories of birds [42] and flowers [23]. Similar improvements are observed in domains where a subset of the categories was used to fine-tune the model. By prompting LLMs in various ways, we generate descriptions that capture visual appearance, habitat, and geographic regions and pair them with existing attributes such as the taxonomic structure of the categories. We systematically evaluate their ability to improve zero-shot cat-egorization in natural domains. Our findings suggest that geographic priors can be just as effective and are complementary to visual appearance. Our method also outperforms prior work on prompt-based tuning of VLMs. We release the benchmark, consisting of 14 datasets at https: //***/cvl-umass/AdaptCLIPZS, which will contribute to future research in zero-shot recognition.

关键词： Fine-grained Classification Large Language Model Multimodal Model vision Language Model Zero Shot Learning

来源：评论

学校读者我要写书评

暂无评论

Grounding Everything: Emerging Localization Properties in vision-Language Transformers

Grounding Everything: Emerging Localization Properties in Vi...

引用

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

作者： Bousselham, Walid Petersen, Felix Ferrari, Vittorio Kuehne, Hilde Univ Bonn Bonn Germany Goethe Univ Frankfurt Frankfurt Germany Stanford Univ Stanford CA 94305 USA Synthesia Io London England MIT IBM Watson AI Lab Cambridge MA USA

ISBN: (纸本)9798350353013;9798350353006

vision-language foundation models have shown remarkable performance in various zero-shot settings such as image retrieval, classification, or captioning. But so far, those models seem to fall behind when it comes to zero-shot localization of referential expressions and objects in images. As a result, they need to be fine-tuned for this task. In this paper, we show that pretrained vision-language (VL) models allow for zero-shot open-vocabulary object localization without any fine-tuning. To leverage those capabilities, we propose a Grounding Everything Module (GEM) that generalizes the idea of value-value attention introduced by CLIPSurgery [17] to a self-self attention path. We show that the concept of self-self attention corresponds to clustering, thus enforcing groups of tokens arising from the same object to be similar while preserving the alignment with the language space. To further guide the group formation, we propose a set of regularizations that allows the model to finally generalize across datasets and backbones. We evaluate the proposed GEM framework on various benchmark tasks and datasets for semantic segmentation. GEM not only outperforms other training-free open-vocabulary localization methods, but also achieves state-of-the-art results on the recently proposed OpenImagesV7 large-scale segmentation benchmark. (1)

关键词： CLIP open-vocabulary zero-shot segmentation vision-language model

来源：评论

学校读者我要写书评

暂无评论

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

EfficientSAM: Leveraged Masked Image Pretraining for Efficie...

引用

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

作者： Xiong, Yunyang Varadarajan, Bala Wu, Lemeng Xiang, Xiaoyu Xiao, Fanyi Zhu, Chenchen Dai, Xiaoliang Wang, Dilin Sun, Fei Iandola, Forrest Krishnamoorthi, Raghuraman Chandra, Vikas Meta AI Res Menlo Pk CA 94025 USA

ISBN: (纸本)9798350353006

Segment Anything Model (SAM) has emerged as a powerful tool for numerous vision applications. A key component that drives the impressive performance for zero-shot transfer and high versatility is a super large Transformer model trained on the extensive high-quality SA-1B dataset. While beneficial, the huge computation cost of SAM model has limited its applications to wider real-world applications. To address this limitation, we propose EfficientSAMs, lightweight SAM models that exhibits decent performance with largely reduced complexity. Our idea is based on leveraging masked image pretraining, SAMI, which learns to reconstruct features from SAM image encoder for effective visual representation learning. Further, we take SAMI-pretrained light-weight image encoders and mask decoder to build EfficientSAMs, and finetune the models on SA-1B for segment anything task. We perform evaluations on multiple vision tasks including image classification, object detection, instance segmentation, and semantic segmentation, and find that our proposed pretraining method, SAMI, consistently outperforms other masked image pretraining methods. On segment anything task such as zero-shot instance segmentation, our EfficientSAMs with SAMI-pretrained lightweight image encoders perform favorably with a significant gain (e.g., similar to 4 AP on COCO/LVIS) over other fast SAM models. Our EfficientSAM code and models are available at here.

关键词： EfficientSAM Masked Image Pretraining SAMI Segment Anything vision Transformer

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500页 << < 27 28 29 30 31 32 33 34 35 36 > >>

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：