检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Kaixin Wang, Hongzhi Li, Ziqi Lu, Yabin Li, Yingze Yan, Yu Guan, Yiming Massive Data Computing Lab Harbin Institute of Technology No. 92 Xidazhi Street Nangang District Heilongjiang Harbin150006 China

research on learned cardinality estimation has achieved significant progress in recent years. However, existing methods still face distinct challenges that hinder their practical deployment in production environments. We conceptualize these challenges as the "Trilemma of Cardinality Estimation", where learned cardinality estimation methods struggle to balance generality, accuracy, and updatability. To address these challenges, we introduce DistJoin, a join cardinality estimator based on efficient distribution prediction using multi-autoregressive models. Our contributions are threefold: (1) We propose a method for estimating both equi and non-equi join cardinality by leveraging the probability distributions of individual tables in a decoupled manner. (2) To meet the requirements of efficient training and inference for DistJoin, we develop Adaptive Neural Predicate Modulation (ANPM), a high-throughput conditional probability distribution estimation model. (3) We formally analyze the variance of existing similar methods and demonstrate that such approaches suffer from variance accumulation issues. To mitigate this problem, DistJoin employs a selectivity-based approach rather than a count-based approach to infer join cardinality, effectively reducing variance. In summary, DistJoin not only represents the first data-driven method to effectively support both equi and non-equi joins but also demonstrates superior accuracy while enabling fast and flexible updates. We evaluate DistJoin on JOB-light and JOB-light-ranges, extending the evaluation to non-equi join conditions. The results demonstrate that our approach achieves the highest accuracy, robustness to data updates, generality, and comparable update and inference speed relative to existing methods. © 2025, CC BY.

关键词： Adaptive modulation

来源：评论

学校读者我要写书评

暂无评论

Identifying Effective Trajectory Predictions Under the Guidance of Trajectory Anomaly Detection Model

TechRxiv

引用

TechRxiv 2022年

作者： Wang, Chunnan Liang, Chen Chen, Xiang Wang, Hongzhi Massive Data Computing Lab Harbin Institute of Technology Harbin China

Trajectory Prediction (TP) is an important research topic in computer vision and robotics fields. Recently, many stochastic TP models have been proposed to deal with this problem and have achieved better performance than the traditional models with deterministic trajectory outputs. However, these stochastic models can generate a number of future trajectories with different qualities. They are lack of self-evaluation ability, that is, to examine the rationality of their prediction results, thus failing to guide users to identify high-quality ones from their candidate results. This hinders them from playing their best in real applications. In this paper, we make up for this defect and propose TPAD, a novel TP evaluation method based on the trajectory Anomaly Detection (AD) technique. In TPAD, we firstly combine the Automated Machine Learning (AutoML) technique and the experience in the AD and TP field to automatically design an effective trajectory AD model. Then, we utilize the learned trajectory AD model to examine the rationality of the predicted trajectories, and screen out good TP results for users. Extensive experimental results demonstrate that TPAD can effectively identify near-optimal prediction results, improving stochastic TP models’ practical application effect. © 2022, CC BY-NC-SA.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Image super‐resolution via dynamic network

引用

CAAI Transactions on Intelligence technology 2024年第4期9卷 837-849页

作者： Chunwei Tian Xuanyu Zhang Qi Zhang Mingming Yang Zhaojie Ju School of Software Northwestern Polytechnical UniversityXi'anChina National Engineering Laboratory for Integrated Aero‐Space‐Ground‐Ocean Big Data Application Technology Xi'anChina Research&Development Institute Northwestern Polytechnical UniversityShenzhenChina School of Economics and Management Harbin Institute of Technology at WeihaiWeihaiChina Tencent AI Lab ShenzhenChina School of Computing University of PortsmouthPortsmouthUK

Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐***,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction *** residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐*** enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying *** prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained ***,a residual learning operation is embedded in the refinement block to prevent long‐term dependency ***,a construction block is responsible for reconstructing high‐quality *** heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital *** results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and *** code of DSRNet can be obtained at https://***/hellloxiaotian/DSRNet.

关键词： CNN dynamic network image super‐resolution lightweight network

来源：评论

学校读者我要写书评

暂无评论

Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging

arXiv

引用

arXiv 2024年

作者： Wang, Bo Tan, Dingwei Kuo, Yen-Ling Sun, Zhaowei Wolfe, Jeremy M. Cham, Tat-Jen Zhang, Mengmi College of Computing and Data Science Nanyang Technological University Singapore Deep NeuroCognition Lab I2R CFAR Agency for Science Technology and Research Singapore Harbin Institute of Technology Harbin China Beijing Institute of Technology Beijing China University of Virginia United States Brigham and Women’s Hospital United States Harvard Medical School United States

Imagine searching a collection of coins for quarters (0.25), dimes (0.10), nickels (0.05), and pennies (0.01)—a hybrid foraging task where observers look for multiple instances of multiple target types. In such tasks, how do target values and their prevalence influence foraging and eye movement behaviors (e.g., should you prioritize rare quarters or common nickels)? To explore this, we conducted human psychophysics experiments, revealing that humans are proficient reward foragers. Their eye fixations are drawn to regions with higher average rewards, fixation durations are longer on more valuable targets, and their cumulative rewards exceed chance, approaching the upper bound of optimal foragers. To probe these decision-making processes of humans, we developed a transformer-based Visual Forager (VF) model trained via reinforcement learning. Our VF model takes a series of targets, their corresponding values, and the search image as inputs, processes the images using foveated vision, and produces a sequence of eye movements along with decisions on whether to collect each fixated item. Our model outperforms all baselines, achieves cumulative rewards comparable to those of humans, and approximates human foraging behavior in eye movements and foraging biases within time-limited environments. Furthermore, stress tests on out-of-distribution tasks with novel targets, unseen values, and varying set sizes demonstrate the VF model’s effective generalization. Our work offers valuable insights into the relationship between eye movements and decision-making, with our model serving as a powerful tool for further exploration of this connection. All data, code, and models are available at https://***/ZhanglabDeepNeuroCoglab/visual-forager. Copyright © 2024, The Authors. All rights reserved.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

A Generative Adversarial Active Learning Method for Effective Outlier Detection

A Generative Adversarial Active Learning Method for Effectiv...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Mohamed Jaward Bah Ji Zhang Ting Yu Feng Xia Zhao Li Shuigeng Zhou Hongzhi Wang Big Data Intelligence Research Center Zhejiang Lab Hangzhou China University of Southern Queensland School of Sciences Toowoomba Australia Institute of Innovation Science and Sustainability Federation University Australia Ballarat Australia Zhejiang University China Fudan University School of Computer Science Shanghai China Harbin Institute of Technology Massive Data Computing Lab China

Outlier detection is an important data mining task, and developing effective methods to detect outliers is challenging in cases where there is insufficient labeled data. Manually labeling the data is labor-intensive and time-consuming. Because of a limited number of labeled samples, the classes are unbalanced, resulting in a class-imbalance problem. Existing methods fail to address these aforementioned issues holistically and fall short in generating quality outlier samples for effective outlier detection accuracy. In this paper, we propose a new solution that tackles these problems. We propose a. Generative Adversarial Active Learning method (DIR-GAAL), which generates Diverse, Informative, and Representative outlier samples through active learning, and employs the mini-max game between the generator and discriminator in a generative adversarial network. We conducted extensive experiments on several benchmark datasets to evaluate the performance of our method. When compared to other benchmark methods, our method consistently demon-strates better outlier detection accuracy without being negatively affected by the class-imbalance problem.

关键词： Learning systems Games Benchmark testing Generative adversarial networks Generators labeling Task analysis

来源：评论

学校读者我要写书评

暂无评论

PCP theorems, SETH and more: Towards proving sub-linear time inapproximability

arXiv

引用

arXiv 2020年

作者： Ma, Hengzhao Li, Jianzhong Research Center of Massive Data Computing Harbin Institute of Technology Nangang HarbinHeilongjiang China

In this paper we propose the PCP-like theorem for sub-linear time inapproximability. Abboud et al. have devised the distributed PCP framework for sub-quadratic time inapproximability. We show that the distributed PCP theorem can be generalized for proving arbitrary polynomial time inapproximability, but fails in the linear case. We prove the sub-linear PCP theorem by adapting from an MA-protocol for the Set Containment problem, and show how to use the theorem to prove both existing and new inapproximability results, exhibiting the power of the sub-linear PCP theorem. Considering the emerging research works on sub-linear time algorithms, the sub-linear PCP theorem is important in guiding the research in sub-linear time approximation algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean label

arXiv

引用

arXiv 2022年

作者： Hu, Shengshan Zhou, Ziqi Zhang, Yechao Zhang, Leo Yu Zheng, Yifeng He, Yuanyuan Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China School of Information Technology Deakin University VIC3216 Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security HUST Wuhan430074 China Cluster and Grid Computing Lab HUST Wuhan430074 China

Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonstrated that deep neural networks (DNNs) are susceptible to adversarial examples, and exploring adversarial attack against deep hashing has attracted many research efforts. Nevertheless, backdoor attack, another famous threat to DNNs, has not been studied for deep hashing yet. Although various backdoor attacks have been proposed in the field of image classification, existing approaches failed to realize a truly imperceptive backdoor attack that enjoys invisible triggers and clean label setting simultaneously, and they also cannot meet the intrinsic demand of image retrieval backdoor. In this paper, we propose BadHash, the first generative-based imperceptible backdoor attack against deep hashing, which can effectively generate invisible and input-specific poisoned images with clean label. Specifically, we first propose a new conditional generative adversarial network (cGAN) pipeline to effectively generate poisoned samples. For any given benign image, it seeks to generate a natural-looking poisoned counterpart with a unique invisible trigger. In order to improve the attack effectiveness, we introduce a label-based contrastive learning network labCLN to exploit the semantic characteristics of different labels, which are subsequently used for confusing and misleading the target model to learn the embedded trigger. We finally explore the mechanism of backdoor attacks on image retrieval in the hash space. Extensive experiments on multiple benchmark datasets verify that BadHash can generate imperceptible poisoned samples with strong attack ability and transferability over state-of-the-art deep hashing schemes. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Prototype-supervised adversarial network for targeted attack of deep hashing

arXiv

引用

arXiv 2021年

作者： Wang, Xunguang Zhang, Zheng Wu, Baoyuan Shen, Fumin Lu, Guangming Harbin Institute of Technology Shenzhen China Peng Cheng Laboratory School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data University of Electronic Science and Technology of China Koala Uran Tech

Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field. In this paper, we propose a novel prototype-supervised adversarial network (ProS-GAN), which formulates a flexible generative architecture for efficient and effective targeted hashing attack. To the best of our knowledge, this is the first generation-based method to attack deep hashing networks. Generally, our proposed framework consists of three parts, i.e., a PrototypeNet, a generator and a discriminator. Specifically, the designed PrototypeNet embeds the target label into the semantic representation and learns the prototype code as the category-level representative of the target label. Moreover, the semantic representation and the original image are jointly fed into the generator for flexible targeted attack. Particularly, the prototype code is adopted to supervise the generator to construct the targeted adversarial example by minimizing the Hamming distance between the hash code of the adversarial example and the prototype code. Furthermore, the generator is against the discriminator to simultaneously encourage the adversarial examples visually realistic and the semantic representation informative. Extensive experiments verify that the proposed framework can efficiently produce adversarial examples with better targeted attack performance and transferability over state-of-the-art targeted attack methods of deep hashing. Copyright © 2021, The Authors. All rights reserved.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Image super-resolution via dynamic network

arXiv

引用

arXiv 2023年

作者： Tian, Chunwei Zhang, Xuanyu Zhang, Qi Yang, Mingming Ju, Zhaojie School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China Research & Development Institute Northwestern Polytechnical University Shenzhen China School of Economics and Management Harbin Institute of Technology at Weihai Weihai264209 China Tencent AI lab Shenzhen China School of Computing University of Portsmouth PortsmouthPO1 3HE United Kingdom

Convolutional neural networks depend on deep network architectures to extract accurate information for image super-resolution. However, obtained information of these convolutional neural networks cannot completely express predicted high-quality images for complex scenes. In this paper, we present a dynamic network for image super-resolution (DSRNet), which contains a residual enhancement block, wide enhancement block, feature refinement block and construction block. The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super-resolution. To enhance robustness of obtained super-resolution model for complex scenes, a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super-resolution model for varying scenes. To prevent interference of components in a wide enhancement block, a refinement block utilizes a stacked architecture to accurately learn obtained features. Also, a residual learning operation is embedded in the refinement block to prevent long-term dependency problem. Finally, a construction block is responsible for reconstructing high-quality images. Designed heterogeneous architecture can not only facilitate richer structural information, but also be lightweight, which is suitable for mobile digital devices. Experimental results show that our method is more competitive in terms of performance, recovering time of image super-resolution and complexity. The code of DSRNet can be obtained at https://***/hellloxiaotian/DSRNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

SFSC: Segment feature sampling classifier for time series classification 4th

SFSC: Segment feature sampling classifier for time series cl...

引用

4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018

作者： Meng, Fanshan Yue, Tianbai Wang, Hongzhi Gao, Hong Li, Yaping Massive Data Computing Research Center Harbin Institute of Technology Xidazhijie. 92 Harbin China

ISBN: (纸本)9789811322020

Time series classification research is important in data mining. However, the existing methods are not fast and accurate enough. Common classification algorithms cannot satisfy the requirements of time series classification. Since the dimensions of each time series sample may be different. Based on this character, we propose a new approach combining the feature sampling algorithm and the random forest classifier (SFSC). To test the efficiency and effectiveness of SFSC, UCR time series datasets are used for our experiments. We also discuss the performance of Dynamic Time Warping (DTW) compared with our approach. We conclude the suitable situations in which our method behaves better. Besides, We discuss the method to determine the best parameters for feature sampling method. The experiment results shows that in most cases, the SFSC algorithm behaves better than DTW and can be used for real-time query and large dataset. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Time series

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：