检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Simin Xu, Huangxinxin Wang, Jiakai Liu, Aishan He, Fazhi Liu, Xianglong Tao, Dacheng State Key Lab of Software Development Environment Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine China School of Computer Science Wuhan University China ***. China

Billions of people are sharing their daily life images on social media every day. However, their biometric information (e.g., fingerprint) could be easily stolen from these images. The threat of fingerprint leakage from social media raises a strong desire for anonymizing shared images while maintaining image qualities, since fingerprints act as a lifelong individual biometric password. To guard the fingerprint leakage, adversarial attack emerges as a solution by adding imperceptible perturbations on images. However, existing works are either weak in black-box transferability or appear unnatural. Motivated by visual perception hierarchy (i.e., high-level perception exploits model-shared semantics that transfer well across models while low-level perception extracts primitive stimulus and will cause high visual sensitivities given suspicious stimulus), we propose FingerSafe, a hierarchical perceptual protective noise injection framework to address the mentioned problems. For black-box transferability, we inject protective noises on fingerprint orientation field to perturb the model-shared high-level semantics (i.e., fingerprint ridges). Considering visual naturalness, we suppress the low-level local contrast stimulus by regularizing the response of Lateral Geniculate Nucleus. Our FingerSafe is the first to provide feasible fingerprint protection in both digital (up to 94.12%) and realistic scenarios (Twitter and Facebook, up to 68.75%). 1 Copyright © 2022, The Authors. All rights reserved.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

arXiv

引用

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

MLAE: MASKED LORA EXPERTS FOR VISUAL PARAMETER-EFFICIENT FINE-TUNING

arXiv

引用

arXiv 2024年

作者： Wang, Junjie Yang, Guangjing Chen, Wentao Yi, Huahui Wu, Xiaohu Lin, Zhouchen Lao, Qicheng Beijing University of Posts and Telecommunications China National Key Lab of General AI School of Intelligence Science and Technology Peking University China Shanghai Jiao Tong University China West China Biomedical Big Data Center West China Hospital Sichuan University China Institute for Artificial Intelligence Peking University China Shanghai AI Laboratory China

In response to the challenges posed by the extensive parameter updates required for full fine-tuning of large-scale pre-trained models, parameter-efficient fine-tuning (PEFT) methods, exemplified by Low-Rank Adaptation (LoRA), have emerged. LoRA simplifies the fine-tuning process but may still struggle with a certain level of redundancy in low-rank matrices and limited effectiveness from merely increasing their rank. To address these issues, a natural idea is to enhance the independence and diversity of the learning process for the low-rank matrices. Therefore, we propose Masked LoRA Experts (MLAE), an innovative approach that applies the concept of masking to visual PEFT. Our method incorporates a cellular decomposition strategy that transforms a low-rank matrix into independent rank-1 submatrices, or "experts", thus enhancing independence. Additionally, we introduce a binary mask matrix that selectively activates these experts during training to promote more diverse and anisotropic learning, based on expert-level dropout strategies. Our investigations reveal that this selective activation not only enhances performance but also fosters a more diverse acquisition of knowledge with a marked decrease in parameter similarity among MLAE, significantly boosting the quality of the model. Remarkably, MLAE achieves new state-of-the-art (SOTA) performance with an average accuracy score of 78.8% on the VTAB-1k benchmark and 90.9% on the FGVC benchmark, surpassing the previous SOTA result by an average of 0.8% on both benchmarks with approximately half parameters. Our code is available at https://***/jie040109/MLAE. Copyright © 2024, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation 24

AUCSeg: AUC-oriented pixel-level long-tail semantic segmenta...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Boyu Han Qianqian Xu Zhiyong Yang Shilong Bao Peisong Wen Yangbangyan Jiang Qingming Huang Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory School of Computer Science and Tech. University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combined compression and encryption of linear wireless sensor network data using autoencoders

引用

Scientific Reports 2025年第1期15卷 1-16页

作者： Shylashree, N. Kumar, Sachin Min, Hong Department of Electronics and Communication RV College of Engineering Affiliated to VTU Belagavi Bengaluru 560059 India Big Data and Machine Learning Lab South Ural State University Chelyabinsk Russian Federation Akian College of Science and Engineering American University of Armenia Yerevan 0019 Armenia School of Computing Gachon University Seongnam South Korea

In a linear wireless sensor network (LWSN), sensor nodes are deployed in a linear fashion to monitor and gather data along a linear path or route. Generally, the base station collects the data from the contiguously placed nodes in the same order. When the sensors are deployed closely and with a gradual variation of sensor data along the route, a high degree of correlation exists among the sensed data. The sensed data sequence can be compressed with very low loss in such a situation. In this paper, a joint compression and encryption method for LWSN data is presented. The method is based on the dimension reduction property of an autoencoder at the bottleneck section. The Encoder part of the trained Autoencoder, housed at the Base Station (BS), reduces the number of data samples at the encoded output. Hence, the data gets compressed at the output of the Encoder. The output of the Encoder is encrypted using an asymmetric encryption that provides immunity to the Chosen Plaintext Attack. Thus, both data compression and encryption are achieved together at the BS. Therefore, the procedure at the BS is denoted as joint compression and encryption. The encrypted data is sent to the Cloud Server for secured storage and further distribution to the End User, where it is decrypted and subsequently decompressed by the Decoder part of the trained Autoencoder. The decompressed data sequence is very nearly equal to the original data sequence. The proposed lossy compression has a mean square reconstruction error of less than 0.5 for compression ratios in the range of 5 to 10. The compression time taken is short even though the Autoencoder training process, which occurs once in a while, takes a relatively long time. © The Author(s) 2025.

关键词： Autoencoder with supervised learning Chosen plaintext attack Integer matrix keys Joint compression and encryption Linear wireless sensor network Secured cloud storage

来源：评论

学校读者我要写书评

暂无评论

Late Mesozoic Tectonic Transfer in the Southern Great Xing'An Range, Ne China: Evidence from Geochronology, Geochemistry and Lu-Hf Isotopes of Magmatic Intrusions in Inner Mongolia

SSRN

引用

SSRN 2023年

作者： Zhao, Zhixiong Dong, Guochen Santosh, M. Bao, Xiangping Ren, Yingwei Xie, Zhuolin School of Earth Science and Mineral Resources China University of Geosciences Beijing100083 China Ulanqab Key Laboratory of Geospatial Big Data Application and Environmental Monitoring Jining Normal University Ulanqab012000 China Department of Earth Science University of Adelaide Adelaide5005 Australia Yonsei Frontier Lab Yonsei University Seoul Korea Republic of

The geodynamic background of the Mesozoic magmatism in the Jarud region of Inner Mongolia remains debated. Here we present zircon U-Pb geochronology, geochemistry and Hf isotope data on the Late Jurassic diorite and Early Cretaceous quartz monzonite porphyry and granite porphyry from the Jarud area to constrain the petrogenesis and tectonic setting. Zircon U-Pb data suggest that the multiphase magmatism extended from the Late Jurassic to Early Cretaceous, i.e., 161.0 ± 1.0 Ma (diorite), 129.9 ± 1.4 Ma (quartz monzonite porphyry), and 125.8 ± 1.1 Ma and 126.8 ± 1.1 Ma (granite porphyry). These rocks are characterized by enrichment of light rare earth and large ion lithophile elements. Based on the geochemistry and Hf isotope data, the diorite with elevated crystallization temperatures (1061 to 1098 ℃), and moderate logfO2 (-22.80 to -7.53) is inferred to have formed by low degree partial melting of depleted mantle wedge metasomatized by fluids at a relatively shallow depth. The quartz monzonite porphyry with moderate crystallization temperatures (755 to 839 °C) and high logfO2 (-18.35 to -9.53) was generated by partial melting of lower crust triggered by depleted mantle-derived basaltic magma underplating, subsequent experienced the fractional crystallization of olivine, pyroxene, Fe-Ti oxides and apatite. The granite porphyry with low crystallization temperatures (643 to 821 °C) and logfO2 (-27.59 to -12.40), is classified as S-type granites, and was sourced from greywacke. The results presented in this study indicate that the Late Jurassic magmatism was related to the southward subduction of the Mongol- Okhotsk Ocean, while the Early Cretaceous magmatic rocks were formed in a post-collision extensional setting. © 2023, The Authors. All rights reserved.

关键词： Quartz

来源：评论

学校读者我要写书评

暂无评论

Backdoor Attack Against Speaker Verification

Backdoor Attack Against Speaker Verification

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Tongqing Zhai Yiming Li Ziqi Zhang Baoyuan Wu Yong Jiang Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China PCL Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781728176055;9781728176062

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party data (e.g., data from the Internet or third-party data company). This raises the question of whether adopting untrusted third-party data can pose a security threat. In this paper, we demonstrate that it is possible to inject the hidden backdoor for infecting speaker verification models by poisoning the training data. Specifically, we design a clustering-based attack scheme where poisoned samples from different clusters will contain different triggers (i.e., pre-defined utterances), based on our understanding of verification tasks. The infected models behave normally on benign samples, while attacker-specified unenrolled triggers will successfully pass the verification even if the attacker has no information about the enrolled speaker. We also demonstrate that existing back-door attacks cannot be directly adopted in attacking speaker verification. Our approach not only provides a new perspective for designing novel attacks, but also serves as a strong baseline for improving the robustness of verification methods.

关键词： Training Mission critical systems Training data Signal processing Robustness data models Internet

来源：评论

学校读者我要写书评

暂无评论

Boosting Factorization Machines via Saliency-Guided Mixup

arXiv

引用

arXiv 2022年

作者： Wu, Chenwang Lian, Defu Ge, Yong Zhou, Min Chen, Enhong Tao, Dacheng School of Data Science University of Science and Technology of China Anhui Hefei230000 China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China Eller College of Management University of Arizona United States Huawei Noah’s Ark Lab Hong Kong JD Explore Academy in *** China University of Sydney Australia

Factorization machines (FMs) are widely used in recommender systems due to their adaptability and ability to learn from sparse data. However, for the ubiquitous non-interactive features in sparse data, existing FMs can only estimate the parameters corresponding to these features via the inner product of their embeddings. Undeniably, they cannot learn the direct interactions of these features, which limits the model’s expressive power. To this end, we first present MixFM, inspired by Mixup, to generate auxiliary training data to boost FMs. Unlike existing augmentation strategies that require labor costs and expertise to collect additional information such as position and fields, these extra data generated by MixFM only by the convex combination of the raw ones without any professional knowledge support. More importantly, if the parent samples to be mixed have non-interactive features, MixFM will establish their direct interactions. Second, considering that MixFM may generate redundant or even detrimental instances, we further put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM). Guided by the customized saliency, SMFM can generate more informative neighbor data. Through theoretical analysis, we prove that the proposed methods minimize the upper bound of the generalization error, which hold a beneficial effect on enhancing FMs. Significantly, we give the first generalization bound of FM, implying the generalization requires more data and a smaller embedding size under the sufficient representation capability. Finally, extensive experiments on five datasets confirm that our approaches are superior to baselines. Besides, the results show that"poisoning" mixed data is likewise beneficial to the FM variants. Copyright © 2022, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Confidence-oriented Contrastive Graph Clustering

Confidence-oriented Contrastive Graph Clustering

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yan-Di Huang Guang-Yu Zhang Dong Huang Chang-Dong Wang Yang Liu Enbo Huang College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Sun Yat-Sen University Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangzhou China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision Nanning Normal University Nanning China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Contrastive clustering has recently been an emerging topic in deep unsupervised learning. Nevertheless, the previous works mostly adopt the stochastic data augmentations, which easily leads to the semantic drift problem by limited transformations. Moreover, these approaches ignore the data distribution information when generating the positive and negative pair-wise samples. In light of this, this paper proposes a simple yet effective unsupervised clustering network termed Confidence-oriented Contrastive Graph Clustering (CoCGC). Particularly, we design an end-to-end network paradigm with un-shared weights, among which a hybrid graph filter is utilized to generate two views of reliable augmentations. Guided by the non-dominated sorting theory, we further construct a confidence-oriented sample set from the latent data distribution perspective. By considering the local density and cluster distribution of the embedding representations, the discriminative sample pairs can be derived from the confidence-oriented sets in a two-view contrastive manner. Finally, a cross-view neighbor contrastive loss is devised for better exploiting the self-supervised network signals. Extensive experimental results on five benchmark datasets demonstrate the effectiveness of our method against the existing state-of-the-art deep graph clustering methods.

关键词： Network topology Semantics Neural networks Reliability theory Reliability engineering Information filters Filtering theory

来源：评论

学校读者我要写书评

暂无评论

REASONER: an explainable recommendation dataset with comprehensive labeling ground truths 23

REASONER: an explainable recommendation dataset with compreh...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Xu Chen Jingsen Zhang Lei Wang Quanyu Dai Zhenhua Dong Ruiming Tang Rui Zhang Li Chen Wayne Xin Zhao Ji-Rong Wen Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China and Gaoling School of Artificial Intelligence Renmin University of China Beijing China Huawei Noah's Ark Lab China www.ruizhang.info Department of Computer Science Hong Kong Baptist University Hong Kong

Explainable recommendation has attracted much attention from the industry and academic communities. It has shown great potential to improve the recommendation persuasiveness, informativeness and user satisfaction. In the past few years, while a lot of promising explainable recommender models have been proposed, the datasets used to evaluate them still suffer from several limitations, for example, the explanation ground truths are not labeled by the real users, the explanations are mostly single-modal and around only one aspect. To bridge these gaps, in this paper, we build a new explainable recommendation dataset, which, to our knowledge, is the first contribution that provides a large amount of real user labeled multi-modal and multi-aspect explanation ground truths. In specific, we firstly develop a video recommendation platform, where a series of questions around the recommendation explainability are carefully designed. Then, we recruit about 3000 high-quality labelers with different backgrounds to use the system, and collect their behaviors and feedback to our questions. In this paper, we detail the construction process of our dataset and also provide extensive analysis on its characteristics. In addition, we develop a library, where many well-known explainable recommender models are implemented in a unified framework. Based on this library, we build several benchmarks for different explainable recommendation tasks. At last, we present many new opportunities brought by our dataset, which are expected to promote the field of explainable recommendation. Our dataset, library and the related documents have been released at https://***/.

关键词：

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：