检索结果-内蒙古大学图书馆

MobileVitV2-Based Fusion of Vision Transformers and Convolutional Neural Networks for Underwater Image Enhancement

学校读者我要写书评

暂无评论

MobileVitV2-Based Fusion of Vision Transformers and Convolut...

International Conference on Information science and Technology (ICIST)

作者： Jiaji Liu Xiaonan Luo Dong Wang Fang Li Ji Li Rushi Lan School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China College of Mathematics and Informatics College of Software Engineering South China Agricultural University Guangzhou China

Acquisition of underwater images presents chal-lenges stemming from inherent distortions and the degradation of color and contrast within the aquatic environment. These challenges, characterized by image quality issues, pose significant obstacles to the training of supervised deep learning models on extensive and diverse datasets, potentially constraining the overall performance of the model. High-quality underwater images play an important role in the development of Autonomous Underwater Vehicles(AUVs}. In this work, we present MobileVitV2 Block Fusion Augmentor and Global-Local Feature Fusion Block with Attent-UNet, which are offered as blocks of generator. Through extensive experiments on different datasets, our proposed method achieves better visual quality, and the method can obtain better Quality images in poorer underwater environments.

关键词：

Improving Factual Error Correction by Learning to Inject Factual Errors

学校读者我要写书评

暂无评论

arXiv 2023年

作者： He, Xingwei Zhang, Qianru Jin, A-Long Ma, Jun Yuan, Yuan Yiu, Siu Ming The University of Hong Kong Hong Kong School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Software Development Environment China Zhongguancun Laboratory China

Factual error correction (FEC) aims to revise factual errors in false claims with minimal editing, making them faithful to the provided evidence. This task is crucial for alleviating the hallucination problem encountered by large language models. Given the lack of paired data (i.e., false claims and their corresponding correct claims), existing methods typically adopt the ‘mask-then-correct’ paradigm. This paradigm relies solely on unpaired false claims and correct claims, thus being referred to as distantly supervised methods. These methods require a masker to explicitly identify factual errors within false claims before revising with a corrector. However, the absence of paired data to train the masker makes accurately pinpointing factual errors within claims challenging. To mitigate this, we propose to improve FEC by Learning to Inject Factual Errors (LIFE), a three-step distantly supervised method: ‘mask-corrupt-correct’. Specifically, we first train a corruptor using the ‘mask-then-corrupt’ procedure, allowing it to deliberately introduce factual errors into correct text. The corruptor is then applied to correct claims, generating a substantial amount of paired data. After that, we filter out low-quality data, and use the remaining data to train a corrector. Notably, our corrector does not require a masker, thus circumventing the bottleneck associated with explicit factual error identification. Our experiments on a public dataset verify the effectiveness of LIFE in two key aspects: Firstly, it outperforms the previous best-performing distantly supervised method by a notable margin of 10.59 points in SARI Final (19.3% improvement). Secondly, even compared to ChatGPT prompted with in-context examples, LIFE achieves a superiority of 7.16 points in SARI Final. Copyright © 2023, The Authors. All rights reserved.

关键词： Error correction

All in One Framework for Multimodal Re-Identification in the Wild

学校读者我要写书评

暂无评论

All in One Framework for Multimodal Re-Identification in the...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： He Li Mang Ye Ming Zhang Bo Du National Engineering Research Center for Multimedia Software Hubei Luojia Laboratory Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China Guangzhou Urban Planning Design Survey Research Institute Guangzhou China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In Re-identification (ReID), recent advancements yield noteworthy progress in both unimodal and cross-modal re-trieval tasks. However, the challenge persists in developing a unified framework that could effectively handle varying multimodal data, including RGB, infrared, sketches, and textual information. Additionally, the emergence of large-scale models shows promising performance in various vision tasks but the foundation model in ReID is still blank. In response to these challenges, a novel multimodal learning paradigm for ReID is introduced, referred to as All-in-One (AIO), which harnesses a frozen pre-trained big model as an encoder, enabling effective multimodal re-trieval without additional fine-tuning. The diverse multi-modal data in AIO are seamlessly tokenized into a unified space, allowing the modality-shared frozen encoder to extract identity-consistent features comprehensively across all modalities. Furthermore, a meticulously crafted ensemble of cross-modality heads is designed to guide the learning trajectory. AIO is the first framework to perform all-in-one ReID, encompassing four commonly used modali-ties. Experiments on cross-modal and multimodal ReID reveal that AIO not only adeptly handles various modal data but also excels in challenging contexts, showcasing exceptional performance in zero-shot and domain generalization scenarios. Code will be available at: https://***/lihe404/AIO.

关键词： computer vision Codes Feature extraction Trajectory Data mining

MV-CC: Mask Enhanced Video Model for Remote Sensing Change Caption

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Ruixun Li, Kaiyu Song, Jiayi Sun, Dongwei Cao, Xiangyong The School of Automation Xi’an Jiaotong University Xi’an710049 China The School of Software Engineering Xi’an Jiaotong University Xi’an710049 China The School of Computer Science and Technology Ministry of Education Key Lab For Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China

Remote sensing image change caption (RSICC) aims to provide natural language descriptions for bi-temporal remote sensing images. Since Change Caption (CC) task requires both spatial and temporal features, previous works follow an encoder-fusion-decoder architecture. They use an image encoder to extract spatial features and the fusion module to integrate spatial features and extract temporal features, which leads to increasingly complex manual design of the fusion module. In this paper, we introduce a novel video model-based paradigm without design of the fusion module and propose a Mask-enhanced Video model for Change Caption (MV-CC). Specifically, we use the off-the-shelf video encoder to simultaneously extract the temporal and spatial features of bi-temporal images. Furthermore, the types of changes in the CC are set based on specific task requirements, and to enable the model to better focus on the regions of interest, we employ masks obtained from the Change Detection (CD) method to explicitly guide the CC model. Experimental results demonstrate that our proposed method can obtain better performance compared with other state-of-the-art RSICC methods. The code is available at https://***/liuruixun/MV-CC. Copyright © 2024, The Authors. All rights reserved.

关键词： Change detection

The Application of Blockchain Technology in the Area of Satellite Remote Sensing Data

学校读者我要写书评

暂无评论

The Application of Blockchain Technology in the Area of Sate...

International Conference on Agro-Geoinformatics

作者： Haiyu He Yongheng Shang Xiaoyu Zhang Jianwei Yin Shuiguang Deng Meng Han School of Software Engineering Zhejiang University Ningbo China Institute of Advanced Technology Zhejiang University Hangzhou China School of Earth Sciences Zhejiang University Hangzhou China School of Computer Science and Technology Zhejiang University Hangzhou China Binjiang Institute of Zhejiang University Hangzhou China

ISBN: (数字)9798350380606

ISBN: (纸本)9798350380613

The growth in the number of satellites and the wide expansion of application areas, driven by continuous progress in Satellite Remote Sensing Data technology, have led to an increasingly obvious trend toward commercialization and marketization. However, as Satellite Remote Sensing Data is an important data asset, it requires higher standards of data security and privacy protection. The traditional centralized data storage and management approach has the risk of a single point of failure, which can easily lead to data tampering and loss, while the lack of a reliable trust mechanism between multi-organizational data parties limits data integration and transactions. Against this background, this paper develops an innovative on-chain-off-chain data distributed storage and transaction system based on blockchain technology, aiming to address the many challenges faced in the area of Satellite Remote Sensing Data. Firstly, by adopting the distributed ledger technology of blockchain, this system ensures the security and integrity of data assets. The decentralized nature of the blockchain allows data to no longer be stored centrally in a single entity, thus avoiding the single-pointof-failure problem of traditional storage methods. Each transaction is recorded on the blockchain, forming an untamperable chain structure, effectively preventing data tampering and loss, and enhancing the overall security of data assets. Secondly, the system in this paper introduces smart contracts in the data transaction behavior, which realizes the automation of data transaction records on the chain through the automated execution of smart contracts. When a data transaction occurs, the smart contract is triggered to execute, and the transaction data can be encrypted and uploaded to the chain, thus safeguarding the privacy information of both parties to the transaction. This mechanism not only improves the security of data but also strengthens the transparency and credibility of the data transact

关键词： Data privacy Satellites Smart contracts Authentication Blockchains Security Reliability

Mitigating Automotive Radar Interference using Onboard Intelligent Reflective Surface

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Maruthi, Shree Prasad Karrthik, G.K. Krishna, A. Vijaya Hassan, Mahbub Yuan, Jinhong Dept. of Electrical and Electronics Engineering WILP Division BITS Pilani India Charcoal Technologies Bengaluru India Bosch Global Software Ltd. Bengaluru India School of Computer Science and Engineering University of New South Wales Sydney Australia School of Electrical Engineering and Telecommunications University of New South Wales Sydney Australia

The use of automotive radars is gaining popularity as a means to enhance a vehicle's sensing capabilities. However, these radars can suffer from interference caused by transmissions from other radars mounted on nearby vehicles. To address this issue, we investigate the use of an onboard intelligent reflective surface (IRS) to artificially increase a vehicle's effective radar cross section (RCS), or its "electromagnetic visibility." Our proposed method utilizes the IRS's ability to form a coherent reflection of the incident radar waveform back towards the source radar, thereby improving radar performance under interference. We evaluated both passive and active IRS options. Passive IRS, which does not support reflection amplification, was found to be counter-productive and actually decreased the vehicle's effective RCS instead of enhancing it. In contrast, active IRS, which can amplify the reflection power of individual elements, effectively combats all types of automotive radar interference when the reflective elements are configured with a 15-35 dB reflection gain. © 2024, CC BY.

关键词： Millimeter waves

Discrete Shuffled Frog Leading Algorithm for Multiple-product Human-robot Collaborative Disassembly Line Balancing Problem

学校读者我要写书评

暂无评论

Discrete Shuffled Frog Leading Algorithm for Multiple-produc...

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Fan, ChenYang Wang, JiaCun Guo, XiWang Qin, ShuJin Zhou, MengChu Qi, Liang Engineering of Liaoning Petrochemical University School of Information and Control Fushun China Engineering of Monmouth University Dept. Computer Science and Software West Long Branch United States Liaoning Petrochemical University Fushun China Monmouth University West Long Branch United States College of Economics and Management of Shangqiu Normal University Shangqiu China Dept. Electrical and Computer Engineering of New Jersey Institute of Technology Newark United States Tech of Shandong University of Science and Technology Dept. Computer Intelligent Sci. & Qingdao China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

With the rapid development of recycling and remanufacturing technologies, disassembly line balancing problems (DLBP) have drawn great attention. Considering the limitation of disassembly by humans or robots alone, this paper focuses on human-robot collaborative disassembly lines. Specifically, this work proposes a multi-product human-robot collaborative disassembly line balancing model to tackle the inflexibility of single product disassembly and inconsistency in recovery values of different product components. Its objective is to maximize disassembly profit. As a commercially available solver, IBM's CPLEX is used to obtain the exact solution of DLBP and verify the correctness of the proposed mathematical model. A discrete shuffled frog leading algorithm is newly designed to solve the sizable problems. Experimental results show that the proposed algorithm has a fast convergence rate and can find solutions consistent with those with CPLEX but requires much less time than the latter, thus advancing the field of disassembly automation. © 2022 IEEE.

关键词： Robots

MyWAL:performance optimization by removing redundant input/output stack in key-value store

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic engineering 2023年第7期24卷 980-993页

作者： Xiao ZHANG Mengyu LI Michael NGULUBE Yonghao CHEN Yiping ZHAO School of Computer Science Northwestern Polytechnical UniversityXi'an 710072China MIIT Key Laboratory of Big Data Storage and Management Northwestern Polytechnical UniversityXi'an 710072China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical UniversityXi'an 710072China School of Software Northwestern Polytechnical UniversityXi'an 710072China

Based on a log-structured merge(LSM)tree,the key-value(KV)storage system can provide high reading performance and optimize random writing *** is widely used in modern data storage systems like e-commerce,online analytics,and real-time *** LSM tree stores new KV data in the memory and flushes to disk in *** prevent data loss in memory if there is an unexpected crash,RocksDB appends updating data in the write-ahead log(WAL)before updating the ***,synchronous WAL significantly reduces writing *** this paper,we present a new WAL mechanism named *** directly manages raw devices(or partitions)instead of saving data on a traditional file *** can avoid useless metadata updating and write data sequentially on *** results show that MyWAL can significantly improve the data writing performance of RocksDB compared to the traditional WAL for small KV data on solid-state disks(SSDs),as much as five to eight times *** non-volatile memory express soild-state drives(NVMe SSDs)and non-volatile memory(NVM),MyWAL can improve data writing performance by 10%–30%.Furthermore,the results of YCSB(Yahoo!Cloud Serving Benchmark)show that the latency decreased by 50%compared with SpanDB.

关键词： Key-value(KV)store Log-structured merge(LSM)tree Non-volatile memory(NVM) Non-volatile memory express soild-state drive(NVMe SSD) Write-ahead log(WAL)

Multi-scale Adaptive Fusion Network for Hyperspectral Image Denoising

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Haodong Gao, Feng Dong, Junyu Du, Qian The School of Computer Science and Technology Ocean University of China Qingdao266100 China The Department of Electrical and Computer Engineering Mississippi State University StarkvilleMS39762 United States The Department of Computer Science Heriot-Watt University Edinburgh United Kingdom Software Engineering Chongqing University Chongqing China Computer Science and Technology Beihang University Beijing China Electrical Engineering The University of Maryland at Baltimore BaltimoreMD United States

Removing the noise and improving the visual quality of hyperspectral images (HSIs) is challenging in academia and industry. Great efforts have been made to leverage local, global or spectral context information for HSI denoising. However, existing methods still have limitations in feature interaction exploitation among multiple scales and rich spectral structure preservation. In view of this, we propose a novel solution to investigate the HSI denoising using a Multi-scale Adaptive Fusion Network (MAFNet), which can learn the complex nonlinear mapping between clean and noisy HSI. Two key components contribute to improving the hyperspectral image denoising: A progressively multiscale information aggregation network and a co-attention fusion module. Specifically, we first generate a set of multiscale images and feed them into a coarse-fusion network to exploit the contextual texture correlation. Thereafter, a fine fusion network is followed to exchange the information across the parallel multiscale subnetworks. Furthermore, we design a co-attention fusion module to adaptively emphasize informative features from different scales, and thereby enhance the discriminative learning capability for denoising. Extensive experiments on synthetic and real HSI datasets demonstrate that the proposed MAFNet has achieved better denoising performance than other state-of-the-art techniques. Our codes are available at https://***/summitgao/MAFNet. © 2023, CC BY.

关键词： Image denoising