检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Wang, Lean Yang, Wenkai Chen, Deli Zhou, Hao Lin, Yankai Meng, Fandong Zhou, Jie Sun, Xu National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Gaoling School of Artificial Intelligence Renmin University of China China Pattern Recognition Center WeChat AI Tencent Inc. China DeepSeek AI China

As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text watermarking techniques have proven reliable in distinguishing whether a text is generated by LLMs by injecting hidden patterns. However, we argue that existing LLM watermarking methods are encoding-inefficient and cannot flexibly meet the diverse information encoding needs (such as encoding model version, generation time, user id, etc.). In this work, we conduct the first systematic study on the topic of Codable Text Watermarking for LLMs (CTWL) that allows text watermarks to carry multi-bit customizable information. First of all, we study the taxonomy of LLM watermarking technologies and give a mathematical formulation for CTWL. Additionally, we provide a comprehensive evaluation system for CTWL: (1) watermarking success rate, (2) robustness against various corruptions, (3) coding rate of payload information, (4) encoding and decoding efficiency, (5) impacts on the quality of the generated text. To meet the requirements of these non-Pareto-improving metrics, we follow the most prominent vocabulary partition-based watermarking direction, and devise an advanced CTWL method named Balance-Marking. The core idea of our method is to use a proxy language model to split the vocabulary into probability-balanced parts, thereby effectively maintaining the quality of the watermarked text. Extensive experimental results show that our method outperforms the baseline under comprehensive evaluation. Our code is available at https://***/lancopku/codable-watermarking-for-llm. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Discriminant analysis with Gabor phase for robust face recognition

Discriminant analysis with Gabor phase for robust face recog...

引用

2012 5th IAPR International Conference on Biometrics, ICB 2012

作者： Zhu, Jianfei Cao, Dong Liu, Sifei Lei, Zhen Li, Stan Z. Institute of Intelligent Information Processing Xidian University Xi'an China Hohai University No. 1 Xikang Road Nanjing Jiangsu Province China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China China Research and Development Center for Internet of Thing China

ISBN: (纸本)9781467303941

This paper presents an occlusion robust image representation method and apply it to face recognition. Inspired from the recent work [15], we propose a Gabor phase difference representation for occlusion robust face recognition. Based on the good ability of Gabor filters to capture image structure and the robustness to image occlusion shown in this paper, Gabor phase features are expected to be discriminative and robust for face representation in occlusion case. Besides, we adopt spectral regression based discriminant analysis with the extracted Gabor phase features to find the most discriminant subspace to classify different faces. In this way, an occlusion robust face image discriminant subspace is derived. Extensive experiments with various occlusion cases show the efficacy of the proposed method. © 2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Interactive object segmentation using iterative adjustable graph cut

Interactive object segmentation using iterative adjustable g...

引用

2011 IEEE Visual Communications and Image processing, VCIP 2011

作者： Shi, Ran Liu, Zhi Xue, Yinzhu Zhang, Xiang School of Communication and Information Engineering Shanghai University Shanghai 200072 China Key Laboratory of Advanced Display and System Application Shanghai University Ministry of Education Shanghai 200072 China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200240 China

ISBN: (纸本)9781457713200

Interactive object segmentation is widely used for extracting any user-interested objects from natural images. A common problem with many interactive segmentation approaches is that the object segmentation quality is degraded due to inaccurate object/background seeds provided by the user. This paper proposes an iterative adjustable graph cut to efficiently solve this problem. First, object/background seeds are initialized based on the object segmentation result obtained with the user-specified scribbles as the interactive input. Then, an iterative seed adjustment scheme is exploited to correct inaccurate seeds and extract new suitable seeds via graph cut, in which the balancing weight between energy terms are adaptively updated to protect stable seeds and speedup the iteration process. Finally, suitable seeds are obtained and graph cut is used to segment the objects. Experimental results demonstrate the better segmentation performance of our approach even if user provides rather rough seeds. © 2011 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Features Fusion Network for Single Image Deraining 10

Multi-scale Features Fusion Network for Single Image Deraini...

引用

10th IEEE Joint International information Technology and Artificial Intelligence Conference, ITAIC 2022

作者： Lai, Yanming Li, Qishen Huang, Hua Li, Qiufeng School of Information Engineering Nanchang Hangkong University Jiangxi Nanchang China School of Software Nanchang Hangkong University Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Jiangxi Nanchang China Nanchang Hangkong University Ministry of Education Key Laboratory of Nondestructive Testing Jiangxi China

ISBN: (数字)9781665422079

ISBN: (纸本)9781665422079

Single image rain removal is an important research direction in the field of computer vision. In this paper, the Multi-scale Features Fusion Network (MFFN) is presented for rain removal. MFFN is mainly composed of Multi-features Fusion Module (MFM) and Dual Attention Module (DAM). In the MFM, we make the improved dense block and the dilation convolutions to form the feature extraction branches, which is conducive to improve the receptive fields of network. Subsequently, the bottom-up connection method is adopted between branches to help different branches make full use of image information. Then, feature branches are merged to fusion different features. DAM is consisted of purposed SA Block and standard SE Block. The purpose of DAM is to reduce the non-rain features which is extracted by the network. Experiments show that MFFN can obtain the better result of rain removal than several advanced methods. © 2022 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Optimized hidden markov model based on constrained particle swarm optimization

arXiv

引用

arXiv 2018年

作者： Chang, Liu Ouzrout, Yacine Nongaillard, Antoine Bouras, Abdelaziz Jiliu, Zhou DISP Laboratory University Lumiere of Lyon 2 France Key Laboratory of Pattern Recognition and Intelligent Information Processing in Sichuan China College of Information Science and Technology Chengdu University Chengdu China

As one of Bayesian analysis tools, Hidden Markov Model (HMM) has been used to in extensive applications. Most HMMs are solved by Baum-Welch algorithm (BWHMM) to predict the model parameters, which is difficult to find global optimal solutions. This paper proposes an optimized Hidden Markov Model with Particle Swarm Optimization (PSO) algorithm and so is called PSOHMM. In order to overcome the statistical constraints in HMM, the paper develops re-normalization and re-mapping mechanisms to ensure the constraints in HMM. The experiments have shown that PSOHMM can search better solution than BWHMM, and has faster convergence speed. Copyright © 2018, The Authors. All rights reserved.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

High-Precision Discrete Convolution Algorithm Based on Moments

High-Precision Discrete Convolution Algorithm Based on Momen...

引用

WRI International Conference on Communications and Mobile Computing, CMC

作者： Jianguo Liu Zhenbing Liu Guoyou Wang Key Laboratory of Education Ministry for Image Processing and Intelligent Control State Key Laboratory of Multispectral Information Processing Technologies Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

Convolution is an important and useful operation in the fields of digital signal processing. In this paper, based on the previous work of performing discrete Fourier transform (DFT) via linear sums of discrete moments, we have made development to eliminate multiplications in discrete Fourier transforms by performing appropriate bit operations and shift operations in binary system, which can be implemented by integer additions of fixed points; then using the convolution theorem with the DFT, we compute the convolution with two DFTs, a point-by-point product, and an inverse DFT. Our algorithm involves fewer multiplications and can deal with arbitrary length signals.

关键词： Convolution Signal processing algorithms Discrete Fourier transforms Very large scale integration Algorithm design and analysis Laboratories Educational technology Digital signal processing Mobile communication Mobile computing

来源：评论

学校读者我要写书评

暂无评论

AN ACTIVE CONTOUR MODEL BASED ON MULTIPLE BOUNDARY MEASURES

AN ACTIVE CONTOUR MODEL BASED ON MULTIPLE BOUNDARY MEASURES

引用

IEEE International Conference on Image processing

作者： Yu Qiao Lei Zhou Jie Yang Yonghui Gao The Key Laboratory of Ministry of Education for System Control and Information Processing Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University

ISBN: (纸本)9781479923427

Weak boundary contrast, inhomogeneous background and overlapped intensity distributions of the object and background are main causes that may lead to failure of boundary detection for many traditional active contour methods. In this paper, we propose a region-based active contour model to address these problems in both local and global ways. A localized active contour framework is developed, in which two local boundary measures are introduced for the evolution of the level set function. These measures are used to select the boundary candidates for boundary preservation such that the evolution of the contour is guided in a reasonable way. The object boundary is determined by a global boundary measure which evaluates the boundary completeness during the entire evolution process. The experiments demonstrate that our method works well against weak boundary contrast, inhomogeneous background and overlapped intensity distributions.

关键词： Region-based active contour model Level set method Local boundary measures Boundary preservation Global boundary measure contour Boundary boundary layer set method boundary contrast Comet Nucleus Tour Edge detection evolution evolution evolution intensity distribution

来源：评论

学校读者我要写书评

暂无评论

Sub-manifold distance based object recognition in clutter

Sub-manifold distance based object recognition in clutter

引用

International Conference on Natural Computation

作者： Zhou, Hua Cai, Chao Ding, Mingyue National Lab for Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Imaging Processing and Intelligence Control Key Laboratory of Education Ministry School of Life Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781424459612

Object recognition is challenging problem in computer vision due to appearance variation and presence of visual clutter and occlusions. Recently manifolds are thought to be fundamental for visual perception, and manifold learning algorithms are developed for discovering intrinsical features. Selective visual attention mechanism provides tools to reduce computation cost and avoid the influence of clutter background. In this paper, we described a new object recognition method, the submanifold distance (SMD) algorithm, which is induced by the visual attention mechanism to provide complex object recognition. Experiments with airport remote sensing images illustrated that our proposed algorithm can recognize complex objects accurately, robustly and quickly. ©2010 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Sequence-level training for non-autoregressive neural machine translation

arXiv

引用

arXiv 2021年

作者： Shao, Chenze Feng, Yang Zhang, Jinchao Meng, Fandong Zhou, Jie Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Pattern Recognition Center WeChat AI Tencent Inc

In recent years, Neural Machine Translation (NMT) has achieved notable results in various translation tasks. However, the word-by-word generation manner determined by the autoregressive mechanism leads to high translation latency of the NMT and restricts its low-latency applications. Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup through generating target words independently and simultaneously. Nevertheless, NAT still takes the word-level cross-entropy loss as the training objective, which is not optimal because the output of NAT cannot be properly evaluated due to the multimodality problem. In this article, we propose using sequence-level training objectives to train NAT models, which evaluate the NAT outputs as a whole and correlates well with the real translation quality. Firstly, we propose training NAT models to optimize sequence-level evaluation metrics (e.g., BLEU) based on several novel reinforcement algorithms customized for NAT, which outperforms the conventional method by reducing the variance of gradient estimation. Secondly, we introduce a novel training objective for NAT models, which aims to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. The BoN training objective is differentiable and can be calculated efficiently without doing any approximations. Finally, we apply a three-stage training strategy to combine these two methods to train the NAT model. We validate our approach on four translation tasks (WMT14 En↔De, WMT16 En↔Ro), which shows that our approach largely outperforms NAT baselines and achieves remarkable performance on all translation tasks. The source code is available at https://***/ictnlp/Seq-NAT. Copyright © 2021, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Images Semantic Segmentation Method Based on Improved Nested UNet

Remote Sensing Images Semantic Segmentation Method Based on ...

引用

2022 International Conference on Geographic information and Remote Sensing Technology, GIRST 2022

作者： Li, Zhongyu Liu, Yang Kuang, Yin Wang, Huajun Liu, Cheng College of Geophysics Chengdu University of Technology Chengdu610059 China College of Computer Science Chengdu Normal University Chengdu611130 China Key Laboratory of interior Layout optimization and Security Institutions of Higher Education of Sichuan Province Sichuan Chengdu611130 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu610106 China Artificial Intelligence Key Laboratory of Sichuan Province Zigong643000 China

ISBN: (纸本)9781510662186

With the development of remote sensing technology, remote sensing images of buildings are of great significance in urban planning, disaster response, and other directions. When we use a neural network containing batch normalization layers for semantic segmentation, the neural network is sensitive to batch size and has low segmentation accuracy for occluded and dense buildings. This paper proposes a method for building segmentation in remote sensing images based on Nested UNet (UNet++) deep neural network. First, the UNet++ network is used to extract features, and the Group Normalization (GN) method is used instead of Batch Normalization (BN) to alleviate the model's sensitivity to batch size. Then the weighted combination of Cross-Entropy Loss (CELoss) and DiceLoss is used as the loss function to improve the feature extraction ability of the neural network for unbalanced buildings. Finally, experiments are carried out on the WHUBuilding dataset. The experimental results show that the improved model (UNet++-GN) improves Mean Intersection over Union (MIoU) and Mean Pixel Accuracy (Macc) by 12.16% and 2.92%, respectively, compared with the original model (UNet++-BN). © 2023 SPIE.

关键词： Feature extraction

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：