检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 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

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques 38

Suppress Content Shift: Better Diffusion Features via Off-th...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 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

Weakly Supervised Video Individual Counting

Weakly Supervised Video Individual Counting

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Liu, Xinyan Li, Guorong Qi, Yuankai Yan, Ziheng Han, Zhenjun van den Hengel, Anton Yang, Ming-Hsuan Huang, Qingming Univ Chinese Acad Sci Beijing Peoples R China Macquarie Univ Sydney NSW Australia UCAS Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Chinese Acad Sci Key Lab Intel Info Proc Inst Comput Tech Beijing Peoples R China Univ Adelaide Australian Inst Machine Learning Adelaide SA Australia Univ Calif Merced Merced CA USA

ISBN: (纸本)9798350353006

Video Individual Counting (VIC) aims to predict the number of unique individuals in a single video. Existing methods learn representations based on trajectory labels for individuals, which are annotation-expensive. To provide a more realistic reflection of the underlying practical challenge, we introduce a weakly supervised VIC task, wherein trajectory labels are not provided. Instead, two types of labels are provided to indicate traffic entering the field of view (inflow) and leaving the field view (outflow). We also propose the first solution as a baseline that formulates the task as a weakly supervised contrastive learning problem under group-level matching. In doing so, we devise an end-to-end trainable soft contrastive loss to drive the network to distinguish inflow, outflow, and the remaining. To facilitate future study in this direction, we generate annotations from the existing VIC datasets SenseCrowd and CroHD and also build a new dataset, UAVVIC. Extensive results show that our baseline weakly supervised method outperforms supervised methods, and thus, little information is lost in the transition to the more practically relevant weakly supervised task. The code and trained model can be found at CGNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sampling-based Estimation of the Number of Distinct Values in Distributed Environment 22

Sampling-based Estimation of the Number of Distinct Values i...

引用

28th ACM SIGKDD Conference on knowledge Discovery and data mining (KKD)

作者： Li, Jiajun Wei, Zhewei Ding, Bolin Dai, Xiening Lu, Lu Zhou, Jingren Renmin Univ China Beijing Peoples R China Alibaba Grp Hangzhou Peoples R China Gaoling Sch Artificial Intelligence Peng Cheng Lab Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China MOE Key Lab Data Engn & Knowledge Engn Beijing Peoples R China

ISBN: (纸本)9781450393850

In data mining, estimating the number of distinct values (NDV) is a fundamental problem with various applications. Existing methods for estimating NDV can be broadly classified into two categories: i) scanning-based methods, which scan the entire data and maintain a sketch to approximate NDV;and ii) sampling-based methods, which estimate NDV using sampling data rather than accessing the entire data warehouse. Scanning-based methods achieve a lower approximation error at the cost of higher I/O and more time. Sampling-based estimation is preferable in applications with a large data volume and a permissible error restriction due to its higher scalability. However, while the sampling-based method is more effective on a single machine, it is less practical in a distributed environment with massive data volumes. For obtaining the final NDV estimators, the entire sample must be transferred throughout the distributed system, incurring a prohibitive communication cost when the sample rate is significant. This paper proposes a novel sketch-based distributed method that achieves sub-linear communication costs for distributed sampling-based NDV estimation under mild assumptions. Our method leverages a sketch-based algorithm to estimate the sample's frequency of frequency in the distributed streaming model, which is compatible with most classical sampling-based NDV estimators. Additionally, we provide theoretical evidence for our method's ability to minimize communication costs in the worstcase scenario. Extensive experiments show that our method saves orders of magnitude in communication costs compared to existing sampling- and sketch-based methods.

关键词： sampling distributed environment NDV communication

来源：评论

学校读者我要写书评

暂无评论

Gene-environment interaction identification via penalized robust divergence

引用

BIOMETRICAL JOURNAL 2022年第3期64卷 461-480页

作者： Ren, Mingyang Zhang, Sanguo Ma, Shuangge Zhang, Qingzhao Univ Chinese Acad Sci Sch Math Sci Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Yale Sch Publ Hlth Dept Biostat New Haven CT USA Xiamen Univ Wang Yanan Inst Studies Econ Sch Econ Dept Stat & Data SciFujian Key Lab Stat Fujian 361005 Peoples R China

In high-throughput cancer studies, gene-environment interactions associated with outcomes have important implications. Some commonly adopted identification methods do not respect the "main effect, interaction" hierarchical structure. In addition, they can be challenged by data contamination and/or long-tailed distributions, which are not uncommon. In this article, robust methods based on gamma-divergence and density power divergence are proposed to accommodate contaminated data/long-tailed distributions. A hierarchical sparse group penalty is adopted for regularized estimation and selection and can identify important gene-environment interactions and respect the "main effect, interaction" hierarchical structure. The proposed methods are implemented using an effective group coordinate descent algorithm. Simulation shows that when contamination occurs, the proposed methods can significantly outperform the existing alternatives with more accurate identification. The proposed approach is applied to the analysis of The Cancer Genome Atlas (TCGA) triple-negative breast cancer data and Gene Environment Association Studies (GENEVA) Type 2 Diabetes data.

关键词： divergence gene-environment interaction hierarchical structure penalized identification robustness

来源：评论

学校读者我要写书评

暂无评论

SOVC: Subject-Oriented Video Captioning

arXiv

引用

arXiv 2023年

作者： Teng, Chang Ma, Yunchuan Li, Guorong Qi, Yuankai Qing, Laiyun Huang, Qingming School of Computer Science and Technology Key Lab of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China School of Computing Macquarie University Australia

Describing video content according to users’ needs is a long-held goal. Although existing video captioning methods have made significant progress, the generated captions may not focus on the entity that users are particularly interested in. To address this problem, we propose a new video captioning task, Subject-Oriented Video Captioning (SOVC), which aims to allow users to specify the describing target via a bounding box. To support this task, we construct two subject-oriented video captioning datasets based on two widely used video captioning datasets: MSVD and MSRVTT, by annotating subjects in each video for each caption. These datasets pave the way for describing users’ interested targets. To tackle this task, we introduce a method tailored to this task, named SOVCNet. It consists of two key components: a subject-oriented sampling module that samples frames related to the subject to minimize irrelevant information;and a subject-oriented encoding module that utilizes the subject areas as hard prompts and integrates learnable soft prompts, enhancing the model’s focus on the subject’s activities and facilitating adaptation to the downstream generation task. Extensive experimental results demonstrate the effectiveness of our method on this new task. Copyright © 2023, The Authors. All rights reserved.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Gupacker: Generalized Unpacking Framework for Android Malware

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 4338-4352页

作者： Zheng, Tao Hou, Qiyu Chen, Xingshu Ren, Hao Li, Meng Li, Hongwei Shen, Changxiang Sichuan Univ Sch Cyber Sci & Engn Chengdu 610065 Peoples R China Sichuan Univ Cyber Sci Res Inst Sch Cyber Sci & Engn Chengdu 610065 Peoples R China Sichuan Univ Key Lab Data Protect & Intelligent Management Minist Educ Chengdu 610065 Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Sch Comp Sci & Informat Engn Minist Educ Hefei 230002 Peoples R China Hefei Univ Technol Intelligent Interconnected Syst Lab Anhui Prov Hefei 230002 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Sichuan Univ Cyber Sci Res Inst Chengdu 610065 Peoples R China

Android malware authors often use packers to evade analysis. Although many unpacking tools have been proposed, they face two significant challenges: 1) They are easily impeded by anti-analysis techniques employed by packers, preventing efficient collection of hidden Dex data. 2) They are typically designed to unpack a specific packer and cannot handle malware packed with mixed packers. Consequently, many packed malware samples evade detection. To bridge this gap, we propose Gupacker , a novel generalized unpacking framework. Gupacker offers a generic solution for first-generation holistic packer by customizing the Android system source code. It identifies the type of packer and selects an appropriate unpacking function, constructs a deeper active call chain to achieve generic unpacking of second-generation function extraction packers, and uses JNI function and instruction monitoring to handle third-generation virtual obfuscation packer. On this basis, we counteract a diverse array of anti-analysis techniques. We conduct extensive experiments on 5K packed Android malware samples, comparing Gupacker with 2 commercial and 4 state-of-the-art academic unpacking tools. The results demonstrate that Gupacker significantly improves the efficiency of Android malware unpacking with acceptable system overhead. We analyze real packed applications based on Gupacker and found several are second-packed by attackers, including WPS for Android, with tens of millions of users. We receive and responsibly report 13 0day vulnerabilities and also assist in the remediation of all vulnerabilities.

关键词： Android malware android packer application unpacking android malware detection Android malware android packer application unpacking android malware detection

来源：评论

学校读者我要写书评

暂无评论

ComCo: Complementary supervised contrastive learning for complementary label learning

引用

NEURAL NETWORKS 2024年 169卷 44-56页

作者： Jiang, Haoran Sun, Zhihao Tian, Yingjie Univ Chinese Acad Sci Sch Math & Sci Beijing 100190 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 101408 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Univ Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China UCAS MOE Social Sci Lab Digital Econ Forecasts & Policy Beijing 100190 Peoples R China

Complementary label learning (CLL) is an important problem that aims to reduce the cost of obtaining largescale accurate datasets by only allowing each training sample to be equipped with labels the sample does not belong. Despite its promise, CLL remains a challenging task. Previous methods have proposed new loss functions or introduced deep learning-based models to CLL, but they mostly overlook the semantic information that may be implicit in the complementary labels. In this work, we propose a novel method, ComCo, which leverages a contrastive learning framework to assist CLL. Our method includes two key strategies: a positive selection strategy that identifies reliable positive samples and a negative selection strategy that skillfully integrates and leverages the information in the complementary labels to construct a negative set. These strategies bring ComCo closer to supervised contrastive learning. Empirically, ComCo significantly achieves better representation learning and outperforms the baseline models and the current state-of-the-art by up to 14.61% in CLL.

关键词： Complementary label learning Weakly supervised learning Contrastive learning Machine learning Representation learning

来源：评论

学校读者我要写书评

暂无评论

Impacts of COVID-19 on SDGs revealed by satellite remote sensing: a bibliometric analysis and systematic review

引用

DISCOVER SUSTAINABILITY 2024年第1期5卷 310页

作者： Chen, Xuejuan Xu, Zheping Jiang, Tian Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Chinese Acad Sci Natl Sci Lib Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Dept Informat Resources Management Beijing 100190 Peoples R China Key Lab New Publishing & Knowledge Serv Scholarly Beijing 100190 Peoples R China

The COVID-19 pandemic and its associated response measures have profoundly impacted both the environment and human life, posing significant challenges to the achievement of the Sustainable Development Goals (SDGs). Several studies have utilized satellite remote sensing to evaluate COVID-19 impacts. In this study, a bibliometric analysis is conducted to reveal the research hotspots limiting to COVID-19 and remote sensing, and further to explore the impacts on SDGs. Results show that the TOP 3 countries of publication amounts are ranked as the United States, China, India. There is a wide range of collaboration in scientific research during this global pandemic, especially in Europe. The publication amounts of research related to SDG 11 are the most, followed by SDG 3, SDG 13, SDG 6, SDG 8, SDG 14, etc. The prevalent topics include the COVID-19 impacts on air quality, water quality, agriculture and food security, climate change, forest ecosystem, and socio-economy. This pandemic brought enormous losses to the socio-economy, which hinders the progress of SDG 8 and SDG 11.5, while had positive or negative effects on goals involving environment and ecosystem, such as SDG 2, SDG 6, SDG 11.6, SDG 13 and SDG 15. Generally, the impacts of COVID-19 on SDGs are comprehensive and systemic, and may depend on the local conditions and management capacity. With satellite remote sensing increasingly vital, global disaster risks can be monitored and managed more effectively to support SDGs in the future.

关键词： Sustainable development goals (SDGs) Bibliometric analysis COVID-19 Impacts Satellite remote sensing

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

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：