检索结果-内蒙古大学图书馆

Reinforcement learning of non-additive joint steganographic embedding costs with attention mechanism

Science China(information Sciences) 2023年第3期66卷 273-286页

作者： Weixuan TANG Bin LI Weixiang LI Yuangen WANG Jiwu HUANG Institute of Artificial Intelligence and Blockchain Guangzhou University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Computer Science and Cyber Engineering Guangzhou University

Image steganography is the art and science of secure communication by concealing information within digital images. In recent years, the techniques of steganographic cost learning have developed rapidly. Although the existing methods can learn satisfactory additive costs, the interplay of different pixels' embedding impacts has not been considered, so the potential of learning may not be fully exploited. To overcome this limitation, in this paper, a reinforcement learning paradigm called Jo Po L(joint policy learning) is proposed to extend the idea of additive cost learning to a non-additive situation. Jo Po L aims to capture the interactions within pixel blocks by defining embedding policies and evaluating contributions of embedding impacts on a block level rather than a pixel level. Then, a policy network is utilized to learn optimal joint embedding policies for pixel blocks through interactions with the environment. Afterwards,these policies can be converted into joint embedding costs for practical message embedding. The structure of the policy network is designed with an effective attention mechanism and incorporated with the domain knowledge derived from traditional non-additive steganographic methods. The environment is responsible for assigning rewards according to the impacts of the sampled joint embedding actions, which are evaluated by the gradient information of a neural network-based steganalyzer. Experimental results show that the proposed non-additive method Jo Po L significantly outperforms the existing additive methods against both feature-based and CNN-based steganalzyers over different payloads.

关键词： information hiding non-additive steganography steganalysis cost learning image processing

来源：评论

学校读者我要写书评

暂无评论

CPAL: Cross-prompting Adapter with LoRAs for RGB+X Semantic Segmentation

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5858-5871页

作者： Liu, Ye Wu, Pengfei Wang, Miaohui Liu, Jun Nanjing University of Posts and Telecommunications School of Automation and Artificial Intelligence Nanjing China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Lancaster University School of Computing and Communications Lancaster United Kingdom

As sensor technology evolves, RGB+X systems combine traditional RGB cameras with another type of auxiliary sensor, which enhances perception capabilities and provides richer information for important tasks such as semantic segmentation. However, acquiring massive RGB+X data is difficult due to the need for specific acquisition equipment. Therefore, traditional RGB+X segmentation methods often perform pretraining on relatively abundant RGB data. However, these methods lack corresponding mechanisms to fully exploit the pretrained model, and the scope of the pretraining RGB dataset remains limited. Recent works have employed prompt learning to tap into the potential of pretrained foundation models, but these methods adopt a unidirectional prompting approach i.e., using X or RGB+X modality to prompt pretrained foundation models in RGB modality, neglecting the potential in non-RGB modalities. In this paper, we are dedicated to developing the potential of pretrained foundation models in both RGB and non-RGB modalities simultaneously, which is non-trivial due to the semantic gap between modalities. Specifically, we present the CPAL (Cross-prompting Adapter with LoRAs), a framework that features a novel bi-directional adapter to simultaneously fully exploit the complementarity and bridging the semantic gap between modalities. Additionally, CPAL introduces low-rank adaption (LoRA) to fine-tune the foundation model of each modal. With the support of these elements, we have successfully unleashed the potential of RGB foundation models in both RGB and non-RGB modalities simultaneously. Our method achieves state-of-the-art (SOTA) performance on five multi-modal benchmarks, including RGB+Depth, RGB+Thermal, RGB+Event, and a multi-modal video object segmentation benchmark, as well as four multi-modal salient object detection benchmarks. The code and results are available at: https://***/abelny56/CPAL. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards Disturbance Rejection in Feature Pyramid Network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 946-958页

作者： Hu, Xiaobo Xu, Wei Gan, Yi Su, Jianbo Zhang, Jun Shanghai Jiao Tong University Joint Institute of UM-SJTU Shanghai200240 China Shanghai Jiao Tong University Research Center of Intelligent Robotics Key Laboratory of System Control and Information Processing Ministry of Education Department of Automation Shanghai200240 China

The multiscale problem is one of the challenging topics in the object detection field. Among the current studies toward this problem, feature pyramid network (FPN) has been shown a superior performance. The core principle of FPN is a mapping for the detectable objects into hierarchy features. These features are designed with different size of receptive fields, which brings good scale invariance in the classification and localization subtasks. However, a disturbance of information dilution is generated by the assignment for the detectable objects into different features. This dilution disturbance is associated with the convolution or pooling operation during the hierarchy feature extraction process. Both of the imprecise localization information in the top features and the fuzzy classification information in the bottom ones limit the performance of FPN. Aiming at the disturbance rejection problem of information dilution, this article presents a feature compensation method. A cross compensation between the semantic information and the localization information in hierarchy features is used to enhance the vanilla FPN. Then, the evaluation metrics in an object detection task are examined. Not only the overall performance, but also the respective metrics for multiscale objects validate a considerable improvement of the FPN with a disturbance compensation mechanism. The experimental results demonstrate an effectiveness of the proposed method in this article. © 2020 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Lidar-Visual-Inertial Odometry with Online Extrinsic Calibration

引用

Journal of Shanghai Jiaotong university(Science) 2023年第1期28卷 70-76页

作者：茅天阳赵文韬王景川陈卫东 Department of Automation Institute of Medical RoboticsShanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China

To achieve precise localization,autonomous vehicles usually rely on a multi-sensor perception system surrounding the mobile *** is a time-consuming process,and mechanical distortion will cause extrinsic calibration ***,we propose a lidar-visual-inertial odometry,which is combined with an adapted sliding window mechanism and allows for online nonlinear optimization and extrinsic *** the adapted sliding window mechanism,spatial-temporal alignment is performed to manage measurements arriving at different *** nonlinear optimization with online calibration,visual features,cloud features,and inertial measurement unit(IMU)measurements are used to estimate the ego-motion and perform extrinsic *** experiments were carried out on both public datasets and real-world *** indicate that the proposed system outperforms state-of-the-art open-source methods when facing challenging sensor-degenerating conditions.

关键词： autonomous vehicles multi-sensor fusion online calibration

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Selection via Adaptive Feature Clustering for High-dimensional Data 5

Unsupervised Feature Selection via Adaptive Feature Clusteri...

引用

5th International Conference on Data Science and information Technology, DSIT 2022

作者： Jia, Hong Weng, Yubin Shenzhen Institute of Artificial Intelligence and Robotics for Society College of Electronics and Information Engineering Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

The purpose of feature selection is to obtain a feature subset from the original data to realize dimension reduction, and at the same time, improve the performance of following machine learning task. Due to the lack of label information, unsupervised feature selection is more challenging. In this paper, the idea of sample clustering is applied to feature space. Clustering the features makes the similarity between features in the same cluster high and that from different clusters low. Subsequently, representative features are selected from each cluster to form the final feature subset. Along this way, an unsupervised feature selection algorithm which considers both the similarity and relevance of different features is proposed. Experiments in comparison with both traditional and novel algorithms on benchmark data sets are performed. The results show the superiority of the proposed method. © 2022 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A Real-time Local Planner Design for Smart Wheelchairs Based on Koopman Bilinear Model Predictive Control

A Real-time Local Planner Design for Smart Wheelchairs Based...

引用

2024 IEEE International Conference on Real-Time Computing and robotics, RCAR 2024

作者： Yu, Guanfeng Zhang, Han Wang, Zehao Wang, Jingchuan Shanghai Jiao Tong University Institute of Medical Robotics Department of Automation China Ministry of Education of China Key Laboratory of System Control and Information Processing China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9798350372601

The paper introduces a Koopman bilinear model predictive control (KBMPC) as a local planner for smart wheelchair systems. This approach leverages the Koopman Operator to streamline the nonlinear terms in MPC, aiming to achieve superior real-time performance. In particular, we employ the Extended Dynamic Mode Decomposition (EDMD) method to approximate the infinite dimensional Koopman operator. To tackle the challenge of designing lifting functions, we systematically utilize the derivatives of known nonlinear structures to methodically derive lifting functions. This systematic approach facilitates the identification of a precise bilinear model. Next, we formulate the corresponding Koopman bilinear MPC problem. Finally, an iterative algorithm is employed to efficiently solve the KBMPC problem. This method linearizes the bilinear model around estimations and iteratively solves the resulting quadratic programming problem to refine estimations. This allows KBMPC to function as a real-time local planner for smart wheelchairs. The prediction of nonlinear terms shows that the identified Koopman bilinear model increases the prediction accuracy. Furthermore, experiments demonstrate the advantages of the designed KBMPC local planner, highlighting its superior real-time performance and predictive capabilities. © 2024 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Improving millimeter-wave imaging quality using the vortex phase method

引用

Defence Technology（防务技术） 2024年第9期39卷 193-202页

作者： Nairui Hu Feng Qi Yelong Wang Zhaoyang Liu Pengxiang Liu Weifan Li Key Laboratory of Terahertz Imaging and Sensing Shenyang 110169China Shenyang Aerospace University Shenyang 110136China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of SciencesShenyang 110169China Shenyang Institute of Automation Chinese Academy of SciencesShenyang 110169China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China University of Chinese Academy of Sciences Beijing 100049China

This paper investigates a new vortex wave imaging approach to improve the imaging quality of small metal targets of size less than 1.5 *** with different spiral phase plates are designed to efficiently transmit vortex beams with orbital angular momentums(OAMs).By analyzing the OAM spectrum of the target,it was discovered that the predominant reflection contains a particular OAM mode that carries abundant azimuthal *** can be explained by the OAM selectivity of the target and the guidance of the vortex transmitting beam.A simple reflection vortex imaging system was designed to capture the phase *** results show that the high image contrast reaches 14.9%,which is twice as high as that of the imaging without *** of simulations and experiments demonstrate that the vortex phase imaging approach proposed in this paper can effectively improve the imaging quality at 80 *** approach is suitable for other millimeter wave imaging systems and is helpful to improve the resolution in anti-terrorism security checks.

关键词： Orbital angular momentums(OAMs)beams Focal plane imaging Spiral phase plates(SPPs) Vortex spectrum

来源：评论

学校读者我要写书评

暂无评论

Semi-Autonomous Navigation Based on Local Semantic Map for Mobile Robot

引用

Journal of Shanghai Jiaotong university(Science) 2025年第1期30卷 27-33页

作者： ZHAO Yanfei XIAO Peng WANG Jingchuan GUO Rui Department of Automation Institute of Medical RoboticsShanghai Jiao Tong UniversityShanghai200240China State Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240China State Grid Intelligence Technology Co. Ltd.Jinan250013China

Mobile robots represented by smart wheelchairs can assist elderly people with mobility *** paper proposes a multi-mode semi-autonomous navigation system based on a local semantic map for mobile robots,which can assist users to implement accurate navigation(e.g.,docking)in the environment without prior *** order to overcome the problem of repeated oscillations during the docking of traditional local path planning algorithms,this paper adopts a mode-switching method and uses feedback control to perform docking when approaching semantic *** last,comparative experiments were carried out in the real *** show that our method is superior in terms of safety,comfort and docking accuracy.

关键词： semi-autonomous navigation mobile robot semantic map voice interaction

来源：评论

学校读者我要写书评

暂无评论

Activation Template Matching Loss for Explainable Face Recognition 17

Activation Template Matching Loss for Explainable Face Recog...

引用

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Lin, Huawei Liu, Haozhe Li, Qiufu Shen, Linlin Computer Vision Institute School of Computer Science and Softwre Enginnering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (纸本)9798350345445

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic Explainable Channel Loss (ECLoss) to construct an explainable face recognition network. The explainable network trained with ECLoss can easily learn the facial part-based representation on the target convolutional layer, where an individual channel can detect a certain face part. Our experiments on dozens of datasets show that ECLoss achieves superior explainability metrics, and at the same time improves the performance of face verification without face alignment. In addition, our visualization results also illustrate the effectiveness of the proposed ECLoss. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion 38

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent D...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：