检索结果-内蒙古大学图书馆

5th International Conference on intelligent computing and Human-Computer Interaction, ICHCI 2024

作者： Zhang, Jiali Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China School of Mathematics and Information Science Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China

ISBN: (纸本)9798350368284

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration 38

Speculative Decoding with CTC-based Draft Model for LLM Infe...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 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

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Visual Prompt Flexible-Modal Face Anti-Spoofing

引用

IEEE Transactions on Dependable and Secure computing 2025年第3期22卷 2597-2606页

作者： Yu, Zitong Cai, Rizhao Cui, Yawen Liu, Ajian Chen, Changsheng Great Bay University School of Computing and Information Technology Dongguan523000 China Nanyang Technological University ROSE Lab School of EEE 639798 Singapore Hong Kong Polytechnic University Kowloon Hong Kong Chinese Academy of Sciences University of Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Beijing100190 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security College of Electronics and Information Engineering Shenzhen518060 China

Recently, vision transformer based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, multimodal face data collected from the real world is often imperfect due to missing modalities from various imaging sensors. Recently, flexible-modal FAS (Yu et al. 2023) has attracted more attention, which aims to develop a unified multimodal FAS model using complete multimodal face data but is insensitive to test-time missing modalities. In this paper, we tackle one main challenge in flexible-modal FAS, i.e., when missing modality occurs either during training or testing in real-world situations. Inspired by the recent success of the prompt learning in language models, we propose Visual Prompt flexible-modal FAS (VP-FAS), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to downstream flexible-modal FAS task. Specifically, both vanilla visual prompts and residual contextual prompts are plugged into multimodal transformers to handle general missing-modality cases, while only requiring less than 4% learnable parameters compared to training the entire model. Furthermore, missing-modality regularization is proposed to force models to learn consistent multimodal feature embeddings when missing partial modalities. Extensive experiments conducted on two multimodal FAS benchmark datasets demonstrate the effectiveness of our VP-FAS framework that improves the performance under various missing-modality cases while alleviating the requirement of heavy model re-training. © 2004-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Identity-Based Signature from Lattices Without Trapdoors 26th

Identity-Based Signature from Lattices Without Trapdoors

引用

26th International Conference on information and Communications Security, ICICS 2024

作者： Luo, Pingbin Chen, Xinjian Susilo, Willy Huang, Qiong College of Mathematics and Informatics South China Agricultural University Guangzhou China Guangzhou Key Laboratory of Intelligent Agriculture Guangzhou510642 China School of Computing and Information Technology University of Wollongong Wollongong Australia

ISBN: (纸本)9789819788002

Currently, the majority of lattice-base identity-based signature (LB-IBS) schemes rely on lattice trapdoor technique introduced by Gentry, Peikert, and Vaikuntanathan. However, this approach significantly impacts computational efficiency. In light of this, we present an alternative method for constructing LB-IBS that does not rely on lattice trapdoors and preimage sampling function. We construct an IBS scheme by employing Lyubashevsky’s signature twice, which is essentially a public key delegation from concatenated Schnorr signatures. In order to optimize the signature size, we describe an adaptation of our scheme in module lattices setting and compression technique. Moreover, our new LB-IBS can combine with Dilithium naturally so that it could carry the advantages of the latter such as side-channel attacks protection. We demonstrate that our construction is provably secure against existential forgery on adaptively chosen message and identity attacks in random oracle model. In comparison with the most efficient LB-IBS scheme (to the best of our knowledge), the signature size of our scheme is 52% smaller and runtime of our scheme is up to 32% faster. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

GP-Net: Global Perceptual Network with Adaptive Gradient Clipping for Emotional Image Classification 8

GP-Net: Global Perceptual Network with Adaptive Gradient Cli...

引用

8th International Conference on intelligent computing and Signal Processing, ICSP 2023

作者： Wang, Xiaohua Yang, Jie Hu, Min Wu, Xia Hefei University of Technology Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer Science and Information Engineering Hefei China

ISBN: (纸本)9798350302455

Traditional image emotion recognition focuses only on the emotion information embedded in the subject or part of the image, while ignoring the global emotion information. In this paper, we propose a new network based on Vision Transformer: a global perception network, containing a main module and a background module. The main module enhances the weighting of objects by showing the interdependencies between modelled channels. The background module further searches for emotional information in the background. In addition, we employ multi-task learning and Adaptive Gradient Clipping to improve the network. Extensive experiments show that our proposed method outperforms the state-of-the-art methods for image sentiment analysis. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Controlled-source electromagnetic noise attenuation via a deep convolutional neural network and high-quality sounding curve screening mechanism

引用

Geophysics 2025年第3期90卷 WA125-WA140页

作者： Liu, Yecheng Li, Diquan Li, Jin Zhang, Xian Central South University Monitoring Ministry of Education Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Changsha China Hunan Provincial Key Laboratory of Non-ferrous Resources and Geological Hazard Detection Changsha China Central South University School of Geoscience and Info-physics Changsha China Hunan Normal University College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan University of Finance and Economics School of Information Technology and Management Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology Changsha China

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of the recorded signal. We develop a novel and effective CSEM noise attenuation method that integrates a deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first uses a DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Because some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data and calculates the corresponding sounding curve and its SV for each segment. The highest-quality sounding curve can be screened out by comparing the SVs of all curves as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, our method is validated with synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by our method. © 2025 Society of Exploration Geophysicists. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards a Self-contained Data-driven Global Weather Forecasting Framework 41

Towards a Self-contained Data-driven Global Weather Forecast...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Xiao, Yi Bai, Lei Xue, Wei Chen, Hao Chen, Kun Chen, Kang Han, Tao Ouyang, Wanli Department of Computer Science and Technology Tsinghua University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China Qinghai University and Intelligent Computing Application Laboratory of Qinghai Province China School of Information Science and Technology Fudan University Shanghai China

Data-driven weather forecasting models are advancing rapidly, yet they rely on initial states (i.e., analysis states) typically produced by traditional data assimilation algorithms. Four-dimensional variational assimilation (4DVar) is one of the most widely adopted data assimilation algorithms in numerical weather prediction centers;it is accurate but computationally expensive. In this paper, we aim to couple the AI forecasting model, FengWu, with 4DVar to build a self-contained data-driven global weather forecasting framework, FengWu-4DVar. To achieve this, we propose an AI-embedded 4DVar algorithm that includes three components: (1) a 4DVar objective function embedded with the FengWu forecasting model and its error representation to enhance efficiency and accuracy;(2) a spherical-harmonic-transform-based (SHT-based) approximation strategy for capturing the horizontal correlation of background error;and (3) an auto-differentiation (AD) scheme for determining the optimal analysis fields. Experimental results show that under the ERA5 simulated observational data with varying proportions and noise levels, FengWu-4DVar can generate accurate analysis fields;remarkably, it has achieved stable self-contained global weather forecasts for an entire year for the first time, demonstrating its potential for real-world applications. Additionally, our framework is approximately 100 times faster than the traditional 4DVar algorithm under similar experimental conditions, highlighting its significant computational efficiency. Copyright 2024 by the author(s)

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

FUZZY ALIGNMENTS IN DIRECTED ACYCLIC GRAPH FOR NON-AUTOREGRESSIVE MACHINE TRANSLATION 11

FUZZY ALIGNMENTS IN DIRECTED ACYCLIC GRAPH FOR NON-AUTOREGRE...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Ma, Zhengrui Shao, Chenze Gui, Shangtong Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Harbin Institute of Technology Shenzhen China

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem. Recently, the structure of directed acyclic graph has achieved great success in NAT, which tackles the multi-modality problem by introducing dependency between vertices. However, training it with negative log-likelihood loss implicitly requires a strict alignment between reference tokens and vertices, weakening its ability to handle multiple translation modalities. In this paper, we hold the view that all paths in the graph are fuzzily aligned with the reference sentence. We do not require the exact alignment but train the model to maximize a fuzzy alignment score between the graph and reference, which takes captured translations in all modalities into account. Extensive experiments on major WMT benchmarks show that our method substantially improves translation performance and increases prediction confidence, setting a new state of the art for NAT on the raw training data. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Lithological Facies Classification Using Attention-Based Gated Recurrent Unit

引用

Tsinghua Science and technology 2024年第4期29卷 1206-1218页

作者： Yuwen Liu Yulan Zhang Xingyuan Mao Xucheng Zhou Jingwen Chang Wenwei Wang Pan Wang Lianyong Qi College of Computer Science and Technology China University of Petroleum(East China)Qingdao 266580China Shandong Provincial University Laboratory for Protected Horticulture Weifang University of Science and TechnologyShouguang 262700China School of Mechanical Electrical and Information EngineeringShandong UniversityWeihai 264209China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of JinanJinan 250022China School of Modern Posts Nanjing University of Posts and TelecommunicationsNanjing 210023China

Lithological facies classification is a pivotal task in petroleum geology, underpinning reservoir characterization and influencing decision-making in exploration and production operations. Traditional classification methods, such as support vector machines and Gaussian process classifiers, often struggle with the complexity and nonlinearity of geological data, leading to suboptimal performance. Moreover, numerous prevalent approaches fail to adequately consider the inherent dependencies in the sequence of measurements from adjacent depths in a well. A novel approach leveraging an attention-based gated recurrent unit (AGRU) model is introduced in this paper to address these challenges. The AGRU model excels by exploiting the sequential nature of well-log data and capturing long-range dependencies through an attention mechanism. This model enables a flexible and context-dependent weighting of different parts of the sequence, enhancing the discernment of key features for classification. The proposed method was validated on two publicly available datasets. Results demonstrate a considerably improvement over traditional methods. Specifically, the AGRU model achieved superior performance metrics considering precision, recall, and F1-score.

关键词： attention mechanism facies classification GRU MLP(multilayer perceptron)

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：