检索结果-内蒙古大学图书馆

7th Asian Conference on Artificial Intelligence Technology, ACAIT 2023

作者： Zhang, Xiaoying Yang, Houqun Li, Xuanyu Yang, Dangui Shen, Jie Xu, Gaodi Hainan University College of Computer Science And Technology Hainan Haikou China Hainan University Haikou Key Laboratory of Deep Learning And Big Data Application Technology Hainan Haikou China

ISBN: (纸本)9798350359145

Increasingly, high-resolution remote sensing images are being used in real life as a result of the continuous advancement of high-definition remote sensing imaging technology in recent years. They play a crucial role in urban planning, agriculture, oceans, ecological protection, and other fields. A growing amount of remote sensing image data has led to a growing interest in using image instance segmentation to decode remote sensing images by automatically extracting valuable information. The present paper examines and analyzes a large number of instance segmentation methods on remote sensing images. It begins with an explanation of the classification and research progress of natural image instance segmentation techniques, which are categorized into two-stage instance segmentation, single-stage instance segmentation, multi-stage instance segmentation and weakly supervised instance segmentation, and also analyzed in terms of their advantages and shortcomings. And then we discussed it in more detail of remote sensing image instance segmentation using deep learning, and it is explained that each of these methods can be classified into three types based on its technical characteristics: methods that combine multiscale feature fusion, methods that combine dilated convolution and methods that combine attention mechanisms, as well as the benefits and limitations of each method. The results of classical experiments on different datasets are presented, along with an explanation of the commonly used datasets and evaluation metrics in instance segmentation. This paper presents an overview of the current problems and challenges associated with remote sensing image instance segmentation, as well as future trends and developments. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing 32

POEM: 1-bit Point-wise Operations based on Expectation-Maxim...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Xu, Sheng Li, Yanjing Zhao, Junhe Zhang, Baochang Guo, Guodong Beihang University Beijing China National Engineering Laboratory for Deep Learning Technology and Application Institute of Deep Learning Baidu Research Beijing China

Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices. To address this issue, we implement XNOR-Net-based binary neural networks (BNNs) for an efficient point cloud processing, but its performance is severely suffered due to two main drawbacks, Gaussian-distributed weights and non-learnable scale factor. In this paper, we introduce point-wise operations based on Expectation-Maximization (POEM) into BNNs for efficient point cloud processing. The EM algorithm can efficiently constrain weights for a robust bi-modal distribution. We lead a well-designed reconstruction loss to calculate learnable scale factors to enhance the representation capacity of 1-bit fully-connected (Bi-FC) layers. Extensive experiments demonstrate that our POEM surpasses existing the state-of-the-art binary point cloud networks by a significant margin, up to 6.7%. © 2021. The copyright of this document resides with its authors.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Single-Stage deep learning Approach for Multiple Treatment and Diagnosis in Panoramic X-ray 23th

A Single-Stage Deep Learning Approach for Multiple Treatment...

引用

23rd International Conference on Intelligent Systems Design and applications, ISDA 2023

作者： Singh, Nripendra Kumar Faisal, Mohammad Hasan, Shamimul Goswami, Gaurav Raza, Khalid Department of Computer Science Jamia Millia Islamia New Delhi India Department of Computer Application Galgotias College of Engineering and Technology Greater Noida India Faculty of Dentistry Jamia Millia Islamia New Delhi India Deep Learning Research Team Synergy Labs Gurugram India

ISBN: (纸本)9783031648120

This work investigates the recognition of multiple dental treatment and diagnosis conditions in a full scan dental panoramic image. In this study, we proposed a single-stage oriented deep learning model for five dental therapies, namely restoration, root canal treatment (RCT), RCT with crown, dental implant (DI), and DI with crown, two dental diagnoses (impacted tooth and tooth bud), and natural teeth without any treatment as tooth class. However, considering all eight classes to achieve a wide range of dental radiology data interpretation results in a highly imbalanced dataset. We considered a custom dataset of 661 dental panoramic images where a frequent category is tooth counted 11,282 times, while the least presence category is DI with the crown having 75 instances. The performance of the proposed work was evaluated with average precision of each treatment and diagnosis class. The result of RCT from the dental treatment category achieved an average precision score of 82.63% and recognition of impacted teeth with an average precision score of 18.78% from the dental diagnosis categories. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Feature Selective Transformer for Semantic Image Segmentation

arXiv

引用

arXiv 2022年

作者： Lin, Fangjian Wu, Tianyi Wu, Sitong Tian, Shengwei Guo, Guodong Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China

Recently, it has attracted more and more attentions to fuse multi-scale features for semantic image segmentation. Various works were proposed to employ progressive local or global fusion, but the feature fusions are not rich enough for modeling multi-scale context features. In this work, we focus on fusing multi-scale features from Transformer-based backbones for semantic segmentation, and propose a Feature Selective Transformer (FeSeFormer), which aggregates features from all scales (or levels) for each query feature. Specifically, we first propose a Scale-level Feature Selection (SFS) module, which can choose an informative subset from the whole multi-scale feature set for each scale, where those features that are important for the current scale (or level) are selected and the redundant are discarded. Furthermore, we propose a Full-scale Feature Fusion (FFF) module, which can adaptively fuse features of all scales for queries. Based on the proposed SFS and FFF modules, we develop a Feature Selective Transformer (FeSeFormer), and evaluate our FeSeFormer on four challenging semantic segmentation benchmarks, including PASCAL Context, ADE20K, COCO-Stuff 10K, and Cityscapes, outperforming the state-of-the-art. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on deep Clustering Based on Image Data 13th

Research on Deep Clustering Based on Image Data

引用

13th International Conference on Computer Engineering and Networks, CENet 2023

作者： Li, Xuanyu Yang, Houqun Zhang, Xiaoying Yang, Dangui Huang, Jianqiang Gan, Lin College of Computer Science and Technology Hainan University Hainan Haikou570228 China Haikou Key Laboratory of Deep Learning and Big Data Application Technology Hainan University Hainan Haikou570228 China Hainan Haikou China Elmore Family School of Computer and Electrical Engineering Purdue University West Lafayette United States

ISBN: (纸本)9789819992386

Clustering is an important branch of unsupervised tasks, aiming at mining deeper relationships and patterns in data. The quality of feature representation based on image datasets often determines the upper limit of clustering tasks. In recent years, the application of deep learning in deep clustering representation learning module has learned better feature representation, which gradually overcomes the limitation of traditional shallow clustering facing high-dimensional unstructured data. deep clustering has become a popular research direction in the unsupervised field in recent years, and high clustering performance has been obtained in the continuous deepening research. The existing deep clustering research is mainly oriented to various fields of artificial intelligence, including natural language processing (NLP), speech recognition (ASR), computer vision (CV), etc. We take the field of computer vision as the entry point, analyze and study the research progress of deep clustering in computer vision (CV), and deconstruct the deep clustering model into two parts: a detailed classification of the feature extraction module from the perspective of network model architecture, while the data space of clustering is used as the entry point to divide the clustering module, and discuss the deep clustering. Finally, we analyze the datasets and evaluation metrics commonly used in experiments to study deep clustering architectures in computer vision. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CATrans: Context and Affinity Transformer for Few-Shot Segmentation

arXiv

引用

arXiv 2022年

作者： Zhang, Shan Wu, Tianyi Wu, Sitong Guo, Guodong Australian National University Canberra Australia Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China

Few-shot segmentation (FSS) aims to segment novel categories given scarce annotated support images. The crux of FSS is how to aggregate dense correlations between support and query images for query segmentation while being robust to the large variations in appearance and context. To this end, previous Transformer-based methods explore global consensus either on context similarity or affinity map between support-query pairs. In this work, we effectively integrate the context and affinity information via the proposed novel Context and Affinity Transformer (CATrans) in a hierarchical architecture. Specifically, the Relation-guided Context Transformer (RCT) propagates context information from support to query images conditioned on more informative support features. Based on the observation that a huge feature distinction between support and query pairs brings barriers for context knowledge transfer, the Relation-guided Affinity Transformer (RAT) measures attention-aware affinity as auxiliary information for FSS, in which the self-affinity is responsible for more reliable cross-affinity. We conduct experiments to demonstrate the effectiveness of the proposed model, outperforming the state-of-the-art methods. © 2022, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention

arXiv

引用

arXiv 2022年

作者： Liu, Kai Wu, Tianyi Liu, Cong Guo, Guodong Sun Yat-Sen University Guangzhou China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window. However, these hand-crafted window partition mechanisms are data-agnostic and ignore their input content, so it is likely that one query maybe attends to irrelevant keys/values. To address this issue, we propose a Dynamic Group Attention (DG-Attention), which dynamically divides all queries into multiple groups and selects the most relevant keys/values for each group. Our DG-Attention can flexibly model more relevant dependencies without any spatial constraint that is used in hand-crafted window based attention. Built on the DG-Attention, we develop a general vision transformer backbone named Dynamic Group Transformer (DGT). Extensive experiments show that our models can outperform the state-of-the-art methods on multiple common vision tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Copyright © 2022, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing

arXiv

引用

arXiv 2023年

作者： Liu, Ajian Tan, Zichang Yu, Zitong Zhao, Chenxu Wan, Jun Liang, Yanyan Lei, Zhen Zhang, Du Li, Stan Z. Guo, Guodong Beijing China The Institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application China The Great Bay University Dongguan523000 China The Mininglamp Academy of Sciences Mininglamp Technology China The Macau University of Science and Technology China The Westlake University China

The availability of handy multi-modal (i.e., RGB-D) sensors has brought about a surge of face anti-spoofing research. However, the current multi-modal face presentation attack detection (PAD) has two defects: (1) The framework based on multi-modal fusion requires providing modalities consistent with the training input, which seriously limits the deployment scenario. (2) The performance of ConvNet-based model on high fidelity datasets is increasingly limited. In this work, we present a pure transformer-based framework, dubbed the Flexible Modal Vision Transformer (FM-ViT), for face anti-spoofing to flexibly target any single-modal (i.e., RGB) attack scenarios with the help of available multi-modal data. Specifically, FM-ViT retains a specific branch for each modality to capture different modal information and introduces the Cross-Modal Transformer Block (CMTB), which consists of two cascaded attentions named Multi-headed Mutual-Attention (MMA) and Fusion-Attention (MFA) to guide each modal branch to mine potential features from informative patch tokens, and to learn modality-agnostic liveness features by enriching the modal information of own CLS token, respectively. Experiments demonstrate that the single model trained based on FM-ViT can not only flexibly evaluate different modal samples, but also outperforms existing single-modal frameworks by a large margin, and approaches the multi-modal frameworks introduced with smaller FLOPs and model parameters. Copyright © 2023, The Authors. All rights reserved.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Instance Segmentation of High-Resolution Remote Sensing Images

Research on Instance Segmentation of High-Resolution Remote ...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Xiaoying Zhang Houqun Yang Xuanyu Li Dangui Yang Jie Shen Gaodi Xu College of Computer Science and Technology Hainan University Haikou China Haikou Key Laboratory of Deep Learning and Big Data Application Technology Hainan University Haikou China

ISBN: (数字)9798350359145

ISBN: (纸本)9798350359152

关键词： Instance segmentation deep learning Training Convolution Buildings Urban planning Vegetation mapping

来源：评论

学校读者我要写书评

暂无评论

Region-level Contrastive and Consistency learning for Semi-Supervised Semantic Segmentation

arXiv

引用

arXiv 2022年

作者： Zhang, Jianrong Wu, Tianyi Ding, Chuanghao Zhao, Hongwei Guo, Guodong College of Computer Science and Technology Jilin University Changchun China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China College of Software Jilin University Changchun China The Institute of Deep Learning Baidu Research China

Current semi-supervised semantic segmentation methods mainly focus on designing pixel-level consistency and contrastive regularization. However, pixel-level regularization is sensitive to noise from pixels with incorrect predictions, and pixel-level contrastive regularization has memory and computational cost with O(pixel num2). To address the issues, we propose a novel region-level contrastive and consistency learning framework (RC2L) for semi-supervised semantic segmentation. Specifically, we first propose a Region Mask Contrastive (RMC) loss and a Region Feature Contrastive (RFC) loss to accomplish region-level contrastive property. Furthermore, Region Class Consistency (RCC) loss and Semantic Mask Consistency (SMC) loss are proposed for achieving region-level consistency. Based on the proposed region-level contrastive and consistency regularization, we develop a region-level contrastive and consistency learning framework (RC2L) for semi-supervised semantic segmentation, and evaluate our RC2L on two challenging benchmarks (PASCAL VOC 2012 and Cityscapes), outperforming the state-of-the-art. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：