检索结果-内蒙古大学图书馆

Efficient Adaptive lab.l Refinement for lab.l Noise Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China UniSA STEM University of South Australia AdelaideSA5095 Australia Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy lab.ls, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy lab.ls while thoroughly learning clean samples. However, this often results in overly complex and difficult-to-train models. To address this issue, we decouple the tasks of avoiding fitting incorrect lab.ls and thoroughly learning clean samples and propose a simple yet highly applicable method called Adaptive lab.l Refinement (ALR). First, inspired by lab.l refurbishment techniques, we update the original hard lab.ls to soft lab.ls using the model’s predictions to reduce the risk of fitting incorrect lab.ls. Then, by introducing the entropy loss, we gradually ‘harden’ the high-confidence soft lab.ls, guiding the model to better learn from clean samples. This approach is simple and efficient, requiring no prior knowledge of noise or auxiliary datasets, making it more accessible compared to Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

HSIGene: A Foundation Model for Hyperspectral Image Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Pang, Li Cao, Xiangyong Tang, datao Xu, Shuang Bai, Xueru Zhou, Feng Meng, Deyu The School of Computer Science and Technology The Ministry of Education Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an710049 China The School of Mathematics and Statistics Northwestern Polytechnical University Shaanxi Xi’an710021 China The National Laboratory of Radar Signal Processing Xidian University Xi’an710071 China The Key Laboratory of Electronic Information Countermeasure and Simulation of the Education Ministry of China Xidian University Xi’an710071 China The School of Mathematics and Statistics The Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an710049 China Guangdong Guangzhou510555 China

Hyperspectral image (HSI) plays a vital role in various fields such as agriculture and environmental monitoring. However, due to the expensive acquisition cost, the number of hyperspectral images is limited, degenerating the performance of downstream tasks. Although some recent studies have attempted to employ diffusion models to synthesize HSIs, they still struggle with the scarcity of HSIs, affecting the reliability and diversity of the generated images. Some studies propose to incorporate multi-modal data to enhance spatial diversity, but spectral fidelity cannot be ensured. In addition, existing HSI synthesis models are typically uncontrollab.e or only support single-condition control, limiting their ability to generate accurate and reliable HSIs. To alleviate these issues, we propose HSIGene, a novel HSI generation foundation model which is based on latent diffusion and supports multi-condition control, allowing for more precise and reliable HSI generation. To enhance the spatial diversity of the training data while preserving spectral fidelity, we propose a new data augmentation method based on spatial super-resolution, in which HSIs are upscaled first, and thus abundant training patches could be obtained by cropping the high-resolution HSIs. In addition, to improve the perceptual quality of the augmented data, we introduce a novel two-stage HSI super-resolution framework, which first applies RGB bands super-resolution and then utilizes our proposed Rectangular Guided Attention Network (RGAN) for guided HSI super-resolution. Experiments demonstrate that the proposed model is capable of generating a vast quantity of realistic HSIs for downstream tasks such as denoising and super-resolution. The code and models are availab.e at https://***/LiPang/HSIGene. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Age and Energy Tradeoff for Short Packet Based Two-Hop Decode-and-Forward Relaying Networks

学校读者我要写书评

暂无评论

Age and Energy Tradeoff for Short Packet Based Two-Hop Decod...

IEEE Conference on Wireless Communications and Networking

作者： Mangang Xie Jie Gong Xiao Ma School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

Real-time and energy-efficient transmissions are two critical demands for status update systems, however it is difficult to meet these requirements simultaneously. This paper focuses on the tradeoff between the average age of information (AoI) and the average energy cost (EC) for two-hop decode-and-forward (DF) relaying networks with short packet transmissions. Both the partial relay selection (PRS) and max-min relay selection (MMRS) schemes are considered. The expressions for the average AoI and the average EC of two-hop relaying networks are derived, and the age-energy tradeoff is also achieved by minimizing the weighted sum of them. Numerical simulations show that both PRS and MMRS schemes have their own advantages to minimize the age and energy cost under different channel conditions, where MMRS is a fairness scheme that takes the channel conditions of two hops into account. In addition, an optimal packet length can always be found to tradeoff the average AoI and average EC in two-hop relaying networks.

关键词： Conferences Numerical simulation information age Real-time systems Energy efficiency Encoding Relays

Mask Approximation Net: A Novel Diffusion Model Approach for Remote Sensing Change Captioning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Dongwei Yao, Jing Zhou, Changsheng Cao, Xiangyong Ghamisi, Pedram School of Computer Science and Technology the Ministry of Education Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Mathematics and Statistics Guangdong University of Technology Guangzhou China Helmholtz-Zentrum Dresden-Rossendorf Freiberg09599 Germany Lancaster Environment Centre Lancaster University LancasterLA1 4YR United Kingdom

Remote sensing image change description represents an innovative multimodal task within the realm of remote sensing processing. This task not only facilitates the detection of alterations in surface conditions, but also provides comprehensive descriptions of these changes, thereby improving human interpretability and interactivity. Generally, existing deep-learning-based methods predominantly utilized a three-stage framework that successively perform feature extraction, feature fusion, and localization from bitemporal images before text generation. However, this reliance often leads to an excessive focus on the design of specific network architectures and restricts the feature distributions to the dataset at hand, which in turn results in limited generalizability and robustness during application. To address these limitations, this paper proposes a novel approach for remote sensing image change detection and description that incorporates diffusion models, aiming to transition the emphasis of modeling paradigms from conventional feature learning to data distribution learning. The proposed method primarily includes a simple multi-scale change detection module, whose output features are subsequently refined by an well-designed diffusion model. Furthermore, we introduce a frequency-guided complex filter module to boost the model performance by managing high-frequency noise throughout the diffusion process. We validate the effectiveness of our proposed method across several datasets for remote sensing change detection and description, showcasing its superior performance compared to existing techniques. The code will be availab.e at MaskApproxNet after a possible publication. Copyright © 2024, The Authors. All rights reserved.

关键词： Change detection

Towards Unified Token Learning for Vision-Language Tracking

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tao, Wei Zhou, Yucheng Wang, Yanlin Zhang, Hongyu Wang, Haofen Zhang, Wenqiang Shanghai Engineering Research Center of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China School of Software Engineering Sun Yat-sen University Guangdong Zhuhai519082 China School of Big Data and Software Engineering Chongqing University Chongqing China College of Design and Innovation Tongji University Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Academy for Engineering and Technology Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University 220 Handan Road Shanghai200433 China

Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i.e., good-practice commits), while the rest do not. On the basis of our empirical study, we discover that training on good-practice commits significantly contributes to the commit message generation. Motivated by this finding, we propose a novel knowledge-aware denoising learning method called KADEL. Considering that good-practice commits constitute only a small proportion of the dataset, we align the remaining training samples with these good-practice commits. To achieve this, we propose a model that learns the commit knowledge by training on good-practice commits. This knowledge model enables supplementing more information for training samples that do not conform to good practice. However, since the supplementary information may contain noise or prediction errors, we propose a dynamic denoising training method. This method composes a distribution-aware confidence function and a dynamic distribution list, which enhances the effectiveness of the training process. Experimental results on the whole MCMD dataset demonstrate that our method overall achieves state-of-the-art performance compared with previous methods. © 2024, CC BY.

关键词： Sampling

Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dong, Jianfeng Wang, Yabing Chen, Xianke Qu, Xiaoye Li, Xirong He, Yuan Wang, Xun The College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Electronic Information and Communications Huazhong University of Science and Technology Hubei430074 China The Key Lab of Data Engineering and Knowledge Engineering Renmin University of China The AIMC Lab. School of Information Renmin University of China Beijing100872 China The Alibaba Group Beijing100102 China

This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlab.led videos. The success of this task depends on cross-modal representation learning that projects both videos and sentences into common spaces for semantic similarity computation. In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval. Inspired by the reading strategy of humans, we propose a Reading-strategy Inspired Visual Representation Learning (RIVRL) to represent videos, which consists of two branches: a previewing branch and an intensive-reading branch. The previewing branch is designed to briefly capture the overview information of videos, while the intensive-reading branch is designed to obtain more in-depth information. Moreover, the intensive-reading branch is aware of the video overview captured by the previewing branch. Such holistic information is found to be useful for the intensive-reading branch to extract more fine-grained features. Extensive experiments on three datasets are conducted, where our model RIVRL achieves a new state-of-the-art on TGIF and VATEX. Moreover, on MSR-VTT, our model using two video features shows comparable performance to the state-of-the-art using seven video features and even outperforms models pre-trained on the large-scale HowTo100M dataset. Code is availab.e at https://***/LiJiaBei-7/rivrl. © 2022, CC BY.

关键词： Video recording

Online Attentive Kernel-Based Temporal Difference Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

Universal deep network for steganalysis of color image based on channel representation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wei, Kangkang Luo, Weiqi Tan, Shunquan Huang, Jiwu The Guangdong Key Lab of Information Security Technology School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Up to now, most existing steganalytic methods are designed for grayscale images, and they are not suitable for color images that are widely used in current social networks. In this paper, we design a universal color image steganalysis network (called UCNet) in spatial and JPEG domains. The proposed method includes preprocessing, convolutional, and classification modules. To preserve the steganographic artifacts in each color channel, in preprocessing module, we firstly separate the input image into three channels according to the corresponding embedding spaces (i.e. RGB for spatial steganography and YCbCr for JPEG steganography), and then extract the image residuals with 62 fixed high-pass filters, finally concatenate all truncated residuals for subsequent analysis rather than adding them together with normal convolution like existing CNN-based steganalyzers. To accelerate the network convergence and effectively reduce the number of parameters, in convolutional module, we carefully design three types of layers with different shortcut connections and group convolution structures to further learn high-level steganalytic features. In classification module, we employ a global average pooling and fully connected layer for classification. We conduct extensive experiments on ALASKA II to demonstrate that the proposed method can achieve state-of-the-art results compared with the modern CNN-based steganalyzers (e.g., SRNet and J-YeNet) in both spatial and JPEG domains, while keeping relatively few memory requirements and training time. Furthermore, we also provide necessary descriptions and many ablation experiments to verify the rationality of the network design. Copyright © 2021, The Authors. All rights reserved.

关键词： Steganography