检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Lou, Meng Zhou, Hong-Yu Yang, Sibei Yu, Yizhou The Artificial Intelligence Laboratory Deepwise Healthcare Beijing China The Department of Computer Science The University of Hong Kong Hong Kong The Shanghai Engineering Research Center of Intelligent Vision and Imaging ShanghaiTech University Shanghai China

Recent studies have integrated convolution into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolution prevents it from dynamically adapting to input variations, resulting in a representation discrepancy between convolution and self-attention as self-attention calculates attention matrices dynamically. Furthermore, when stacking token mixers that consist of convolution and self-attention to form a deep network, the static nature of convolution hinders the fusion of features previously generated by self-attention into convolution kernels. These two limitations result in a suboptimal representation capacity of the constructed networks. To find a solution, we propose a lightweight Dual Dynamic Token Mixer (D-Mixer) that aggregates global information and local details in an input-dependent way. D-Mixer works by applying an efficient global attention module and an input-dependent depthwise convolution separately on evenly split feature segments, endowing the network with strong inductive bias and an enlarged effective receptive field. We use D-Mixer as the basic building block to design TransXNet, a novel hybrid CNN-Transformer vision backbone network that delivers compelling performance. In the ImageNet-1K image classification task, TransXNet-T surpasses Swin-T by 0.3% in top-1 accuracy while requiring less than half of the computational cost. Furthermore, TransXNet-S and TransXNet-B exhibit excellent model scalability, achieving top-1 accuracy of 83.8% and 84.6% respectively, with reasonable computational costs. Additionally, our proposed network architecture demonstrates strong generalization capabilities in various dense prediction tasks, outperforming other state-of-the-art networks while having lower computational costs. Our code will be available at https://***/LMMMEng/TransXNet. © 2023, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via vision Transformer

arXiv

引用

arXiv 2024年

作者： Qiu, Yuhang Chen, Honghui Dong, Xingbo Lin, Zheng Liao, Iman Yi Tistarelli, Massimo Jin, Zhe The Anhui Provincial Key Laboratory of Artificial Intelligence School of Artificial Intelligence Anhui University Hefei230093 China The Faculty of Engineering Monash University Wellington Road ClaytonVIC3800 Australia The Department of Physics and Information Engineering Fuzhou University Fuzhou350108 China The Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong The School of Computer Science University of Nottingham Malaysia Campus Semenyih43500 Malaysia The Computer Vision Laboratory University of Sassari Sassari07100 Italy

Determining dense feature points on fingerprints used in constructing deep fixed-length representations for accurate matching, particularly at the pixel level, is of significant interest. To explore the interpretability of fingerprint matching, we propose a multi-stage interpretable fingerprint matching network, namely Interpretable Fixed-length Representation for Fingerprint Matching via vision Transformer (IFViT), which consists of two primary modules. The first module, an interpretable dense registration module, establishes a vision Transformer (ViT)-based Siamese Network to capture long-range dependencies and the global context in fingerprint pairs. It provides interpretable dense pixel-wise correspondences of feature points for fingerprint alignment and enhances the interpretability in the subsequent matching stage. The second module takes into account both local and global representations of the aligned fingerprint pair to achieve an interpretable fixed-length representation extraction and matching. It employs the ViTs trained in the first module with the additional fully connected layer and retrains them to simultaneously produce the discriminative fixed-length representation and interpretable dense pixel-wise correspondences of feature points. Extensive experimental results on diverse publicly available fingerprint databases demonstrate that the proposed framework not only exhibits superior performance on dense registration and matching but also significantly promotes the interpretability in deep fixed-length representations-based fingerprint matching. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Online Self-distillation and Self-modeling for 3D Brain Tumor Segmentation

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Pang, Yan Li, Yunhao Huang, Teng Liang, Jiaming Wang, Zhen Dong, Changyu Kuang, Dongyang Hu, Ying Chen, Hao Lei, Tim Wang, Qiong The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China The School of Artificial Intelligence Guangzhou University China The Zhejiang Lab Hangzhou China Sun Yat-sen University China The Department of Computer Science and Engineering The Department of Chemical and Biological Engineering Hong Kong University of Science and Technology China The Department of Electrical Engineering University of Colorado Denver United States

In the specialized domain of brain tumor segmentation, supervised segmentation approaches are hindered by the limited availability of high-quality labeled data, a condition arising from data privacy concerns, significant costs, and ethical issues. In response to this challenge, this paper presents a training framework that adeptly integrates a plug-and-play component, MOD, into current supervised learning models, boosting their efficacy in scenarios with limited data. The MOD consists of an Online Tokenizer and a Dense Predictor, which employs self-distillation and self-modeling on masked patches, promoting swift convergence and efficient representation learning. During the inference phase, the plug-and-play MOD component is excluded, preserving the computational efficiency of the original model without incurring extra processing costs. We substantiated the value of our approach through experiments on leading 3D brain tumor segmentation baselines. Remarkably, models augmented with the MOD consistently showcased superior results, achieving elevated Dice coefficients and HD95 scores on two datasets: BraTS 2021 and MSD 2019 Task-01 Brain Tumor. Code: https://***/aigzhusmart/MOD © 2013 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report 17th

Efficient Single-Image Depth Estimation on Mobile Devices, ...

引用

17th European Conference on computer vision, ECCV 2022

作者： Ignatov, Andrey Malivenko, Grigory Timofte, Radu Treszczotko, Lukasz Chang, Xin Ksiazek, Piotr Lopuszynski, Michal Pioro, Maciej Rudnicki, Rafal Smyl, Maciej Ma, Yujie Li, Zhenyu Chen, Zehui Xu, Jialei Liu, Xianming Jiang, Junjun Shi, XueChao Xu, Difan Li, Yanan Wang, Xiaotao Lei, Lei Zhang, Ziyu Wang, Yicheng Huang, Zilong Luo, Guozhong Yu, Gang Fu, Bin Li, Jiaqi Wang, Yiran Huang, Zihao Cao, Zhiguo Conde, Marcos V. Sapozhnikov, Denis Lee, Byeong Hyun Park, Dongwon Hong, Seongmin Lee, Joonhee Lee, Seunggyu Chun, Se Young Computer Vision Lab ETH Zürich Zürich Switzerland AI Witchlabs Zollikerberg Switzerland University of Wuerzburg Wuerzburg Germany TCL Research Europe Warsaw Poland Harbin Institute of Technology Harbin China Xiaomi Inc. Beijing China Tencent GY-Lab Shenzhen China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of

ISBN: (纸本)9783031250651

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 m. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Self-Ensembling Depth Completion Via Density-Aware Consistency

SSRN

引用

SSRN 2023年

作者： Zhang, Xuanmeng Zheng, Zhedong Jiang, Minyue Ye, Xiaoqing The ReLER Laboratory Australian Artificial Intelligence Institute University of Technology SydneyNSW2007 Australia The Sea-NExT Joint Lab The Department of Computer Science School of Computing National University of Singapore Singapore117417 Singapore The Department of Computer Vision Technology Baidu Inc. Beijing100085 China

Depth completion can predict a dense depth map by taking a sparse depth map and the aligned RGB image as input, but the acquisition of ground truth annotations is labor-intensive and non-scalable. Therefore, we resort to semi-supervised learning, where we only need to annotate a few images and leverage massive unlabeled data without ground truth labels to facilitate model learning. In this paper, we propose SEED, a SElf-Ensembling Depth completion framework to enhance the generalization of the model on unlabeled data. Specifically, SEED contains a pair of the teacher and student models, which are given high-density and low-density sparse depth maps as input respectively. The main idea underpinning SEED is to enforce the density-aware consistency by encouraging consistent prediction across different-density input depth maps. One empirical challenge is that the pseudodepth labels produced by the teacher model inevitably contain wrong depth values, which would mislead the convergence of the student model. To resist the noisy labels, we propose an automatic method to measure the reliability of the generated pseudo-depth labels adaptively. By leveraging the discrepancy of prediction distributions, we model the pixel-wise uncertainty map as the prediction variance and rectify the training process from noisy labels explicitly. To our knowledge, we are among the early semi-supervised attempts on the depth completion task. Extensive experiments on both outdoor and indoor datasets demonstrate that SEED consistently improves the performance of the baseline model by a large margin and even is on par with several fully-supervised methods. © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Nightwatch with YOLOv8: Real-Time Vehicle Detection and Speed Analysis for Safer Roads

Nightwatch with YOLOv8: Real-Time Vehicle Detection and Spee...

引用

Ubiquitous Networking (UNet), International Conference on

作者： Fouad Agramelal Mohamed Sadik Soumia Mouloudi Youssef Moubarak Saad Abouzahir NEST Research Group ENSEM Hassan II University of Casablanca Casablanca Morocco Laboratory of Information Technologies ENSA University of Chouaib Doukkali El Jadida Morocco Department of Computer Vision Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

ISBN: (数字)9798350356144

ISBN: (纸本)9798350356151

The heavy electric energy consumption of street-lights has prompted the scientific community to develop various control methods. Among these, zoning control, where light follows road users, has emerged as a promising approach due to its significant energy-saving potential. However, existing research often relies on fixed illumination zones based on speed limits or imprecise methods to locate road users. In this paper, we propose a zoning control method based on computer vision and speed measurement to address these issues. We first calibrate the camera using a semi-automatic PnP method to accurately measure distances. Next, we employ a YOLOv8 model trained on a nighttime dataset to detect vehicles in real time and measure their speeds. The results demonstrate significant energy reduction while ensuring road safety.

关键词： Training Hands Lighting Energy measurement Cameras Real-time systems Time measurement Road safety Safety Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents

arXiv

引用

arXiv 2023年

作者： Jemni, Sana Khamekhem Ammar, Sourour Souibgui, Mohamed Ali Kessentini, Yousri Cheddad, Abbas Digital Research Center of Sfax B.P. 275 Sakiet Ezzit Sfax3021 Tunisia Laboratory of Signals systems Artificial Intelligence and networks Sfax Tunisia Multimedia Information systems and Advanced Computing Laboratory Tunisia Computer Vision Center Computer Science Department Universitat Autònoma de Barcelona Spain Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden

Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of annotated training data. However, in the case of historical manuscripts, there is a lack of annotated corpus for training. To handle the data scarcity issue, we investigate the merits of the self-supervised learning to extract useful representations of the input data without relying on human annotations and then using these representations in the downstream task. We propose ST-KeyS, a masked auto-encoder model based on vision transformers where the pretraining stage is based on the mask-and-predict paradigm, without the need of labeled data. In the fine-tuning stage, the pre-trained encoder is integrated into a siamese neural network model that is fine-tuned to improve feature embedding from the input images. We further improve the image representation using pyramidal histogram of characters (PHOC) embedding to create and exploit an intermediate representation of images based on text attributes. In an exhaustive experimental evaluation on three widely used benchmark datasets (Botany, Alvermann Konzilsprotokolle and George Washington), the proposed approach outperforms state-of-the-art methods trained on the same datasets. © 2023, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models

arXiv

引用

arXiv 2024年

作者： Sun, Wangtao Zhang, Chenxiang Zhang, Xueyou Yu, Xuanqing Huang, Ziyang Xu, Haotian Chen, Pei He, Shizhu Zhao, Jun Liu, Kang The Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China CAS Engineering Laboratory for Intelligent Industrial Vision Institute of Automation Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering Texas A&M University United States Shanghai Artificial Intelligence Laboratory China Xiaohongshu Inc China AI Lab AIGility Cloud Innovation Beijing China

Although Large Language Models (LLMs) have demonstrated strong instruction-following ability, they are further supposed to be controlled and guided by inferential rules in real-world scenarios to be safe, accurate, and intelligent. This demands the possession of inferential rule-following capability of LLMs. However, no prior work has made a clear evaluation of the inferential rule-following capability of LLMs. Previous studies that try to evaluate the inferential rule-following capability of LLMs fail to distinguish the inferential rule-following scenarios from the instruction-following scenarios. Therefore, this paper first clarifies the concept of inferential rule-following and proposes a comprehensive benchmark, RuleBench, to evaluate a diversified range of inferential rule-following abilities. Our experimental results on a variety of LLMs show that they are still limited in following rules. Our analysis based on the evaluation results provides insights into the improvements for LLMs toward a better inferential rule-following intelligent agent. We further propose Inferential Rule-Following Tuning (IRFT). The experimental results show that through IRFT, LLMs can learn abstract inferential rule-following abilities from purely synthetic data and then generalize to RuleBench. The data and code can be found at: https://***/r/llm-rulefollowing-B3E3/ Copyright © 2024, The Authors. All rights reserved.

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

St-Keys: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents

SSRN

引用

SSRN 2023年

作者： Jemni, Sana Khamekhem Ammar, Sourour Souibgui, Mohamed Ali Kessentini, Yousri Cheddad, Abbas Digital Research Center of Sfax B.P. 275 Sakiet Ezzit Sfax3021 Tunisia SM@RTS: Laboratory of Signals systeMs aRtificial Intelligence and neTworkS MIR@CL: Multimedia InfoRmation systems and Advanced Computing Laboratory Computer Vision Center Computer Science Department Universitat Aut`onoma de Barcelona Spain Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden

Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of annotated training data. However, in the case of historical manuscripts, there is a lack of annotated corpus for training. To handle the data scarcity issue, we investigate the merits of the self-supervised learning to extract useful representations of the input data without relying on human annotations and then using these representations in the downstream task. We propose ST-KeyS, a masked auto-encoder model based on vision transformers where the pretraining stage is based on the mask-and-predict paradigm, without the need of labeled data. In the fine-tuning stage, the pre-trained encoder is integrated into a siamese neural network model that is fine-tuned to improve feature embedding from the input images. We further improve the image representation using pyramidal histogram of characters (PHOC) embedding to create and exploit an intermediate representation of images based on text attributes. In an exhaustive experimental evaluationon three widely used benchmark datasets (Botany, Alvermann Konzilsprotokolle and George Washington), the proposed approach outperforms state-of-the-art methods trained on the same datasets. © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

arXiv

引用

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

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：