检索结果-内蒙古大学图书馆

Fast signal recovery from saturated measurements by linear loss and nonconvex penalties

学校读者我要写书评

暂无评论

arXiv 2018年

作者： He, Fan Huang, Xiaolin Liu, Yipeng Yan, Ming Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University The MOE Key Laboratory of System Control and Information Processing Shanghai200240 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China The Department of Computational Mathematics Science and Engineering Michigan State University MI United States

Sign information is the key to overcoming the inevitable saturation error in compressive sensing systems, which causes information loss and results in bias. For sparse signal recovery from saturation, we propose to use a linear loss to improve the effectiveness from existing methods that utilize hard constraints/hinge loss for sign consistency. Due to the use of linear loss, an analytical solution in the update progress is obtained, and some nonconvex penalties are applicable, e.g., the minimax concave penalty, the 0 norm, and the sorted 1 norm. Theoretical analysis reveals that the estimation error can still be bounded. Generally, with linear loss and nonconvex penalties, the recovery performance is significantly improved, and the computational time is largely saved, which is verified by the numerical experiments. Copyright © 2018, The Authors. All rights reserved.

关键词： Compressed sensing

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Wenkai Bi, Xiaohan Lin, Yankai Chen, Sishuo Zhou, Jie Sun, Xu Gaoling School of Artificial Intelligence Renmin University of China Beijing China Center for Data Science Peking University China Pattern Recognition Center WeChat AI Tencent Inc. China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and security of LLM-based agents during applications. However, the safety issues of LLM-based agents are currently under-explored. In this work, we take the first step to investigate one of the typical safety threats, backdoor attack, to LLM-based agents. We first formulate a general framework of agent backdoor attacks, then we present a thorough analysis of different forms of agent backdoor attacks. Specifically, compared with traditional backdoor attacks on LLMs that are only able to manipulate the user inputs and model outputs, agent backdoor attacks exhibit more diverse and covert forms: (1) From the perspective of the final attacking outcomes, the agent backdoor attacker can not only choose to manipulate the final output distribution, but also introduce the malicious behavior in an intermediate reasoning step only, while keeping the final output correct. (2) Furthermore, the former category can be divided into two subcategories based on trigger locations, in which the backdoor trigger can either be hidden in the user query or appear in an intermediate observation returned by the external environment. We implement the above variations of agent backdoor attacks on two typical agent tasks including web shopping and tool utilization. Extensive experiments show that LLM-based agents suffer severely from backdoor attacks and such backdoor vulnerability cannot be easily mitigated by current textual backdoor defense algorithms. This indicates an urgent need for further research on the development of targeted defenses against backdoor attacks on LLM-based agents.3 Warning: This paper may contain biased content. © 2024, CC BY.

关键词：

Lower bounds on some van der waerden numbers based on quadratic residues

学校读者我要写书评

暂无评论

Journal of Combinatorial Mathematics and Combinatorial Computing 2012年 83卷 23-31页

作者： Liang, Meilian Xu, Xiaodong Shao, Zehui Xiu, Baoxin School of Mathematics and Information Science Guangxi University Nanning 530004 China Guangxi Academy of Sciences Nanning 530007 China Key Laboratory of Pattern Recognition and Intelligent Information Processing School of Information Science and Technology Chengdu University Chengdu 610106 China College of Information System and Management National University of Defense Technology Changsha 410073 China

The van der Waerden number W(r, k) is the least integer N such that every r-coloring of {1,2, • • •, N} contains a monochromatic arithmetic progression of length at least k. Rabung gave a method to obtain lower bounds on W(2,k) based on quadratic residues, and performed computations on all primes no greater than 20117. By improving the efficiency of the algorithm of Rabung, we perform the computation for all primes up to 6 x 107, and obtain lower bounds on W(2, k) for k between 11 and 23.

关键词： Computational efficiency

Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lan, Zhibin Niu, Liqiang Meng, Fandong Zhou, Jie Zhang, Min Su, Jinsong School of Informatics Xiamen University China Pattern Recognition Center WeChat AI Tencent Inc China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Xiamen University Ministry of Culture and Tourism China Institute of Computer Science and Technology Soochow University China

In-image machine translation (IIMT) aims to translate an image containing texts in source language into an image containing translations in target language. In this regard, conventional cascaded methods suffer from issues such as error propagation, massive parameters, and difficulties in deployment and retaining visual characteristics of the input image. Thus, constructing end-to-end models has become an option, which, however, faces two main challenges: 1) the huge modeling burden, as it is required to simultaneously learn alignment across languages and preserve the visual characteristics of the input image;2) the difficulties of directly predicting excessively lengthy pixel sequences. In this paper, we propose Translatotron-V(ision), an end-to-end IIMT model consisting of four modules. In addition to an image encoder, and an image decoder, our model contains a target text decoder and an image tokenizer. Among them, the target text decoder is used to alleviate the language alignment burden, and the image tokenizer converts long sequences of pixels into shorter sequences of visual tokens, preventing the model from focusing on low-level visual features. Besides, we present a two-stage training framework for our model to assist the model in learning alignment across modalities and languages. Finally, we propose a location-aware evaluation metric called Structure-BLEU to assess the translation quality of the generated images. Experimental results demonstrate that our model achieves competitive performance compared to cascaded models with only 70.9% of parameters, and significantly outperforms the pixel-level end-to-end IIMT model. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

Learning data-adaptive nonparametric kernels

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Huang, Xiaolin Gong, Chen Yang, Jie Li, Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Automation Tsinghua University

Kernel methods have been extensively used in a variety of machine learning tasks such as classification, clustering, and dimensionality reduction. For complicated practical tasks, the traditional kernels, e.g., Gaussian kernel and sigmoid kernel, or their combinations are often not sufficiently flexible to fit the data. In this paper, we present a Data-Adaptive Nonparametric Kernel (DANK) learning framework in a data-driven manner. To be specific, in model formulation, we impose an adaptive matrix on the kernel/Gram matrix in an entry-wise strategy. Since we do not specify the formulation of the adaptive matrix, each entry in the adaptive matrix can be directly and flexibly learned from the data. Therefore, the solution space of the learned kernel is largely expanded, which makes our DANK model flexible to capture the data with different local statistical properties. Specifically, the proposed kernel learning framework can be seamlessly embedded to support vector machines (SVM) and support vector regression (SVR), which has the capability of enlarging the margin between classes and reducing the model generalization error. Theoretically, we demonstrate that the objective function of our DANK model embedded in SVM/SVR is gradient-Lipschitz continuous. Thereby, the training process for kernel and parameter learning in SVM/SVR can be efficiently optimized in a unified framework. Further, to address the scalability issue in nonparametric kernel learning framework, we decompose the entire optimization problem in DANK into several smaller easy-to-solve problems, so that our DANK model can be efficiently approximated by this partition. The effectiveness of this approximation is demonstrated by both empirical studies and theoretical guarantees. Experimentally, the proposed DANK model embedded in SVM/SVR achieves encouraging performance on various classification and regression benchmark datasets when compared with other representative kernel learning based algorithms. Copyrig

关键词： Matrix algebra

Corrigendum to “FGPNet: A weakly supervised fine-grained 3D point clouds classification network” [pattern recognition 139 (2023) 109509]

学校读者我要写书评

暂无评论

pattern recognition 2024年 151卷

作者： Huihui Shao Jing Bai Rusong Wu Jinzhe Jiang Hongbo Liang the School of Computer Science and Engineering North Minzu University Yinchuan 750021 China the Key Laboratory of Images Processing and Pattern Recognition Laboratory Commission: IPPRLab North Minzu University Yinchuan 750021 China

Learning with asymmetric kernels: Least squares and feature interpretation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Mingzhen He, Fan Shi, Lei Huang, Xiaolin Suykens, Johan A.K. Institute Of Image Processing And Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Shanghai Key Laboratory For Contemporary Applied Mathematics Fudan University Shanghai200433 China School Of Mathematical Sciences Fudan University Shanghai200433 China KU Leuven LeuvenB-3001 Belgium

Asymmetric kernels naturally exist in real life, e.g., for conditional probability and directed graphs. However, most of the existing kernel-based learning methods require kernels to be symmetric, which prevents the use of asymmetric kernels. This paper addresses the asymmetric kernel-based learning in the framework of the least squares support vector machine named AsK-LS, resulting in the first classification method that can utilize asymmetric kernels directly. We will show that AsK-LS can learn with asymmetric features, namely source and target features, while the kernel trick remains applicable, i.e., the source and target features exist but are not necessarily known. Besides, the computational burden of AsK-LS is as cheap as dealing with symmetric kernels. Experimental results on the Corel database, directed graphs, and the UCI database will show that, in the case asymmetric information is crucial, the proposed AsK-LS can learn with asymmetric kernels and performs much better than the existing kernel methods that have to do symmetrization to accommodate asymmetric kernels. © 2022, CC BY.

关键词： Directed graphs

A generalization theory based on independent and task-identically distributed assumption

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zheng, Guanhua Sang, Jitao Li, Houqiang Yu, Jian Xu, Changsheng University of Science and Technology of China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Hefei230026 China National Lab of Pattern Recognition Institute of Automation CAS Beijing100190 China University of Chinese Academy of Sciences

—Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Classification (of information)

Efficient spatialtemporal context modeling for action recognition?

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Congqi Lu, Yue Zhang, Yifan Jiang, Dongmei Zhang, Yanning Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Lab on Speech and Image Information Processing School of Computer Science Northwestern Poly-technical University Xi'an710129 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing100190 China

Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between any two points brings huge cost in computation and memory, especially for action recognition, where there is an additional temporal dimension. Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition. The global context is factorized into sparse relation maps. We model the relationship between points in the same line along the direction of horizon, vertical and depth at each time, which forms a 3D criss-cross structure, and duplicate the same operation with recurrent mechanism to transmit the relation between points in a line to a plane finally to the whole spatiotemporal space. Compared with the non-local method, the proposed RCCA-3D module reduces the number of parameters and FLOPs by 25% and 30% for video context modeling. We evaluate the performance of RCCA-3D with two latest action recognition networks on three datasets and make a thorough analysis of the architecture, obtaining the optimal way to factorize and fuse the relation maps. Comparisons with other state-of-the-art methods demonstrate the effectiveness and efficiency of our model. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning