检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Lijun Jiang, Wei Yi, Jinfeng Yang, Tianbao National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China *** Beijing100101 China Department of Computer Science The University of Iowa Iowa CityIA52242 United States

In this paper, we investigate an online prediction strategy named as Discounted-Normal-Predictor (Kapralov and Panigrahy, 2010) for smoothed online convex optimization (SOCO), in which the learner needs to minimize not only the hitting cost but also the switching cost. In the setting of learning with expert advice, Daniely and Mansour (2019) demonstrate that Discounted-Normal-Predictor can be utilized to yield nearly optimal regret bounds over any interval, even in the presence of switching costs. Inspired by their results, we develop a simple algorithm for SOCO: Combining online gradient descent (OGD) with different step sizes sequentially by Discounted-Normal-Predictor. Despite its simplicity, we prove that it is able to minimize the adaptive regret with switching cost, i.e., attaining nearly optimal regret with switching cost on every interval. By exploiting the theoretical guarantee of OGD for dynamic regret, we further show that the proposed algorithm can minimize the dynamic regret with switching cost in every interval. Copyright © 2022, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment

arXiv

引用

arXiv 2024年

作者： Zhou, Kanglei Wang, Liyuan Zhang, Xingxing Shum, Hubert P.H. Li, Frederick W.B. Li, Jianguo Liang, Xiaohui State Key Laboratory of VR Technology and Systems Beihang University China Department of Computer Science and Technology Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University China Department of Computer Science Durham University United Kingdom Children’s Hospital of Capital Institute of Pediatrics China Zhongguancun Laboratory China

Action Quality Assessment (AQA) evaluates diverse skills but models struggle with non-stationary data. We propose Continual AQA (CAQA) to refine models using sparse new data. Feature replay preserves memory without storing raw inputs. However, the misalignment between static old features and the dynamically changing feature manifold causes severe catastrophic forgetting. To address this novel problem, we propose Manifold-Aligned Graph Regularization (MAGR), which first aligns deviated old features to the current feature manifold, ensuring representation consistency. It then constructs a graph jointly arranging old and new features aligned with quality scores. Experiments show MAGR outperforms recent strong baselines with up to 6.56%, 5.66%, 15.64%, and 9.05% correlation gains on the MTL-AQA, FineDiving, UNLV-Dive, and JDM-MSA split datasets, respectively. This validates MAGR for continual assessment challenges arising from non-stationary skill variations. Code is available at https://***/ZhouKanglei/MAGR_CAQA. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach

Webly Supervised Fine-Grained Recognition: Benchmark Dataset...

引用

International Conference on computer Vision (ICCV)

作者： Zeren Sun Yazhou Yao Xiu-Shen Wei Yongshun Zhang Fumin Shen Jianxin Wu Jian Zhang Heng Tao Shen School of Computer Science and Engineering Nanjing University of Science and Technology State Key Laboratory for Novel Software Technology Nanjing University University of Electronic Science and Technology of China University of Technology Sydney

ISBN: (纸本)9781665428132

Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets. Especially for fine-grained recognition, which targets at distinguishing subordinate categories, it will significantly reduce the labeling costs by leveraging free web data. Despite its significant practical and research value, the webly supervised fine-grained recognition problem is not extensively studied in the computer vision community, largely due to the lack of high-quality datasets. To fill this gap, in this paper we construct two new benchmark webly supervised fine-grained datasets, termed WebFG-496 and WebiNat-5089, respectively. In concretely, WebFG-496 consists of three sub-datasets containing a total of 53,339 web training images with 200 species of birds (Web-bird), 100 types of aircrafts (Web-aircraft), and 196 models of cars (Web-car). For WebiNat-5089, it contains 5089 sub-categories and more than 1.1 million web training images, which is the largest webly supervised fine-grained dataset ever. As a minor contribution, we also propose a novel webly supervised method (termed "Peer-learning") for benchmarking these datasets. Comprehensive experimental results and analyses on two new benchmark datasets demonstrate that the proposed method achieves superior performance over the competing baseline models and states-of-the-art. Our benchmark datasets and the source codes of Peer-learning have been made available at https://***/NUST-Machine-Intelligence-laboratory/weblyFG-dataset.

关键词： Training Deep learning Knowledge engineering computer vision Image recognition Target recognition Neural networks

来源：评论

学校读者我要写书评

暂无评论

Webly supervised fine-grained recognition: Benchmark datasets and an approach

arXiv

引用

arXiv 2021年

作者： Sun, Zeren Yao, Yazhou Wei, Xiu-Shen Zhang, Yongshun Shen, Fumin Wu, Jianxin Zhang, Jian Shen, Heng Tao School of Computer Science and Engineering Nanjing University of Science and Technology State Key Laboratory for Novel Software Technology Nanjing University University of Electronic Science and Technology of China University of Technology Sydney

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Instance Learning with Adaptive Recurrent Pooling for Medical Image Classification

Deep Multi-Instance Learning with Adaptive Recurrent Pooling...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yi Ding Lu Zhao Liming Yuan Xianbin Wen School of Computer Science and Engineering Tianjin University of Technology Tianjin China Key Laboratory of Computer Vision and System Ministry of Education Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China School of Computer and Information Engineering Tianjin Chengjian University Tianjin China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Recently, deep multi-instance neural networks have been successfully applied for medical image classification, where only image-level labels rather than fine-grained patch-level labels are available for use. One key issue for these multi-instance neural networks is how to aggregate all patch (instance) features into an entire image (bag) representation, referred to as multi-instance pooling, e.g., max, mean, and attention based pooling. Nevertheless, these multi-instance pooling operations do not take the structural information within an image into account. This is obviously inappropriate for medical image classification since there often exist certain dependencies among regional patches/lesions. We propose an adaptive recurrent pooling based deep multi-instance neural network in this paper. In this network, we first extract multi-view global structural features from every bag using the self-attention mechanism, and then aggregate these multi-view features into a whole bag representation based on the adaptive recurrent pooling operation in order to further capture the contextual information within the bag. Moreover, we introduce the cross-normalization operation used in the Unit Force Operated Vision Transformer into the self-attention module to reduce its computational complexity. We have experimentally evaluated the performance of the proposed network on three medical image datasets, namely UCSB breast, Messidor, and Colon cancer. The results demonstrate the advantage of our network over current state-of-the-art deep multi-instance networks in terms of classification accuracy and interpretability.

关键词： Technological innovation Adaptive systems Aggregates Neural networks Force Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

MOL-AE: Auto-encoder based molecular representation learning with 3D cloze test objective 24

MOL-AE: Auto-encoder based molecular representation learning...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Junwei Yang Kangjie Zheng Siyu Long Zaiqing Nie Ming Zhang Xinyu Dai Wei-Ying Ma Hao Zhou School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University-Anker Embodied AI Lab Peking University School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University Institute for AI Industry Research (AIR) Tsinghua University and PharMolix Inc. Institute for AI Industry Research (AIR) Tsinghua University

3D molecular representation learning has gained tremendous interest and achieved promising performance in various downstream tasks. A series of recent approaches follow a prevalent framework: an encoder-only model coupled with a coordinate denoising objective. However, through a series of analytical experiments, we prove that the encoderonly model with coordinate denoising objective exhibits inconsistency between pre-training and downstream objectives, as well as issues with disrupted atomic identifiers. To address these two issues, we propose MOL-AE for molecular representation learning, an auto-encoder model using positional encoding as atomic identifiers. We also propose a new training objective named 3D Cloze Test to make the model learn better atom spatial relationships from real molecular substructures. Empirical results demonstrate that MOL-AE achieves a large margin performance gain compared to the current state-of-the-art 3D molecular modeling approach. The source codes of MOL-AE are publicly available at https://***/yjwtheonly/MolAE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-View Representation Learning for Multi-Instance Learning with Applications to Medical Image Classification

Multi-View Representation Learning for Multi-Instance Learni...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Lu Zhao Liming Yuan Zhenliang Li Xianbin Wen School of Computer and Information Engineering Tianjin Chengjian University Tianjin China School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China Key Laboratory of Computer Vision and System Ministry of Education Tianjin China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Multi-Instance Learning (MIL) is a weakly supervised learning paradigm, in which every training example is a labeled bag of unlabeled instances. In typical MIL applications, instances are often used for describing the features of regions/parts in a whole object, e.g., regional patches/lesions in an eye-fundus image. However, for a (semantically) complex part the standard MIL formulation puts a heavy burden on the representation ability of the corresponding instance. To alleviate this pressure, we still adopt a bag-of-instances as an example in this paper, but extract from each instance a set of representations using $1 \times1$ convolutions. The advantages of this tactic are two-fold: i) This set of representations can be regarded as multi-view representations for an instance; ii) Compared to building multi-view representations directly from scratch, extracting them automatically using $1 \times1$ convolutions is more economical, and may be more effective since $1 \times1$ convolutions can be embedded into the whole network. Furthermore, we apply two consecutive multi-instance pooling operations on the reconstituted bag that has actually become a bag of sets of multi-view representations. We have conducted extensive experiments on several canonical MIL data sets from different application domains. The experimental results show that the proposed framework outperforms the standard MIL formulation in terms of classification performance and has good interpretability.

关键词： Training Representation learning Retinopathy Supervised learning Buildings Diabetes Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Predictive analysis for race detection in software-defined networks

引用

science China(Information sciences) 2019年第6期62卷 34-53页

作者： Gongzheng LU Lei XU Yibiao YANG Baowen XU State Key Laboratory of Novel Software Technology Nanjing University School of Computer Engineering Suzhou Vocational University

Race condition remains one kind of the most common concurrency bugs in software-defined networks(SDNs). The race conditions can be exploited to lead to security and reliability risks. However,the race conditions are notoriously difficult to detect. The existing race detectors for SDNs have limited detection capability. They can only detect the races in the original traces(observed traces) and cause false negatives. In this study, we present a predictive analysis framework called SDN-predict for race detection in SDNs. By encoding the order between the specified network events in SDNs as constraint, we formulate race detection as a constraint solving problem. In addition to detecting the races in the original trace, our framework can also detect the races in the feasible traces got from reordering the events in the original trace while satisfying the consistency requirements of trace. Moreover, we formally prove that our predictive analysis framework is sound and can achieve the maximal possible detection capability for any sound dynamic race detector with respect to the same trace. We evaluate our framework on a set of traces collected from three SDN controllers(POX, Floodlight, ONOS), running 5 representative applications including reactive and proactive applications in large networks, on three different network topologies. These experiments show that our framework has higher race detection capability than exisiting SDN race detector-SDNRacer, and detects more 1173 races. These 1173 races were previously undetected and confirmed by checking the race graphs.

关键词： constraint solving predictive analysis race detection software-defined networks

来源：评论

学校读者我要写书评

暂无评论

Effective Ambiguity Attack Against Passport-based DNN Intellectual Property Protection Schemes through Fully Connected Layer Substitution

Effective Ambiguity Attack Against Passport-based DNN Intell...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yiming Chen Jinyu Tian Xiangyu Chen Jiantao Zhou Department of Computer and Information Science State Key Laboratory of Internet of Things for Smart City University of Macau Faculty of Innovation Engineering Macau University of Science and Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences

Since training a deep neural network (DNN) is costly, the well-trained deep models can be regarded as valuable intellectual property (IP) assets. The IP protection associated with deep models has been receiving increasing attentions in recent years. Passport-based method, which replaces normalization layers with passport layers, has been one of the few protection solutions that are claimed to be secure against advanced attacks. In this work, we tackle the issue of evaluating the security of passport-based IP protection methods. We propose a novel and effective ambiguity attack against passport-based method, capable of successfully forging multiple valid passports with a small training dataset. This is accomplished by inserting a specially designed accessory block ahead of the passport parameters. Using less than 10% of training data, with the forged passport, the model exhibits almost indistinguishable performance difference (less than 2%) compared with that of the authorized passport. In addition, it is shown that our attack strategy can be readily generalized to attack other IP protection methods based on watermark embedding. Directions for potential remedy solutions are also given.

关键词：

来源：评论

学校读者我要写书评

暂无评论

20-1: A novel liquid crystal planar display structure based on fringe field effect

引用

SID Symposium Digest of Technical Papers 2024年第S1期55卷 171-173页

作者： An-ran LI Xin-yi YU Lachezar Komitov Abhishek K SRIVASTAVA State Key Laboratory of Advanced Displays and Optoelectronics Technologies and Centre for Display Research Department of Electronics and Computer Engineering The Hong Kong University of Science and Technology Hong Kong S.A.R China Department of Physics University of Gothenburg Gothenburg Sweden

The liquid crystal display (LCD) continues to hold a prominent position in the display industry. These years' key research topic is the fringe field effect, which aims to improve the LCD's performance. A new LCD structure utilizing the fringe field effect has been identified as a promising solution. This structure allows for the control of the electromagnetic field of the liquid crystal cell by regulating the voltage of the Circular-Hole and Planar Electrode cell (CHPEC). This innovative structure is comprised of nematic liquid crystals (LCs) with negative dielectric anisotropy, a two-electrode system consisting of a Circular-Hole ITO structure on the top layer and a Planar structure on the bottom layer, and a SiO2 porous structure. Finite element simulation tests have verified the electric field strength, transmittance, and contrast of the cell and the matrix structure, meeting the design objectives. This breakthrough has significant potential for application in the display field.

关键词： LCD Fringe field effect Circular-Hole Electrode

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：