检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Qian, Biao Wang, Yang Yin, Hongzhi Hong, Richang Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology China The University of Queensland

Online knowledge Distillation (OKD) improves the involved models by reciprocally exploiting the difference between teacher and student. Several crucial bottlenecks over the gap between them — e.g., Why and when does a large gap harm the performance, especially for student? How to quantify the gap between teacher and student? — have received limited formal study. In this paper, we propose Switchable Online knowledge Distillation (SwitOKD), to answer these questions. Instead of focusing on the accuracy gap at test phase by the existing arts, the core idea of SwitOKD is to adaptively calibrate the gap at training phase, namely distillation gap, via a switching strategy between two modes — expert mode (pause the teacher while keep the student learning) and learning mode (restart the teacher). To possess an appropriate distillation gap, we further devise an adaptive switching threshold, which provides a formal criterion as to when to switch to learning mode or expert mode, and thus improves the student’s performance. Meanwhile, the teacher benefits from our adaptive switching threshold and keeps basically on a par with other online arts. We further extend SwitOKD to multiple networks with two basis topologies. Finally, extensive experiments and analysis validate the merits of SwitOKD for classification over the state-of-the-arts. Our code is available at https://***/hfutqian/SwitOKD. Copyright © 2022, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

TREC: transient redundancy elimination-based convolution 22

TREC: transient redundancy elimination-based convolution

引用

Proceedings of the 36th International Conference on Neural information Processing Systems

作者： Jiawei Guan Feng Zhang Jiesong Liu Hsin-Hsuan Sung Ruofan Wu Xiaoyong Du Xipeng Shen Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China Computer Science Department North Carolina State University

ISBN: (纸本)9781713871088

The intensive computations in convolutional neural networks (CNNs) pose challenges for resource-constrained devices; eliminating redundant computations from convolution is essential. This paper gives a principled method to detect and avoid transient redundancy, a type of redundancy existing in input data or activation maps and hence changing across inferences. By introducing a new form of convolution (TREC), this new method makes transient redundancy detection and avoidance an inherent part of the CNN architecture, and the determination of the best configurations for redundancy elimination part of CNN backward propagation. We provide a rigorous proof of the robustness and convergence of TREC-equipped CNNs. TREC removes over 96% computations and achieves 3.51× average speedups on microcontrollers with minimal (about 0.7%) accuracy loss.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic SLAM Based on Compensated Segmentation and Geometric Constraints in Dynamic Environments

Semantic SLAM Based on Compensated Segmentation and Geometri...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Baofu Fang Shuai Zhou Hao Wang School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology) Hefei China

Most of the existing slam algorithms are designed based on the assumption of a static environment, this strong assumption limits the practical application of most slam systems. The main reason is that moving objects will cause feature mismatch in the pose estimation process, which in turn affects the accuracy of localization and mapping. In this paper, we propose a SLAM algorithm in a dynamic environment. First, we use the BlendMask network to detect potential moving objects to generate masks for dynamic objects. The geometrically constrained joint optical flow method is used to detect dynamic feature points. Secondly, aiming at the failure of semantic segmentation network segmentation, a missed detection compensation algorithm based on the invariance of adjacent frame speed is proposed. Finally, a keyframe selection strategy is proposed to construct a semantic octree graph containing only static objects. We evaluate our algorithm on TUM RGB-D and real scene datasets. The experimental results show that the algorithm has high accuracy and real-time performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RGB-D SLAM Method Based on Feature Association in Dynamic Environment

RGB-D SLAM Method Based on Feature Association in Dynamic En...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Baofu Fang Hao Wang School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Hefei China

Simultaneous localization and mapping (SLAM) is one of the current research hotspots. However, in visual SLAM for dynamic environments, inaccurate detection of object motion states and incomplete dynamic region culling will lead to large localization errors. To address these issues, this paper proposes an RGB-D SLAM method based on feature association. The method has strongly correlated features in time and space according to the input image sequence. Using the moving probability of the feature points in the previous frame, the movement of the feature points in the current frame is calculated in combination with the dynamic corner points screened in the current frame. Then, the motion state of the object is determined according to the proportion of different feature points. Then combined with semantic information and object depth information, the fast search method is used to obtain accurate dynamic regions. Finally, the selected effective feature points are used to estimate the camera pose and establish a static map of the environment. This paper evaluates the robustness and accuracy of our method on the TUM dataset and real environment, and the results show that our method can significantly improve the system tracking effect and reduce the system tracking error compared with other SLAM methods in dynamic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embedding VLAD in Transformer for Video Question Answering

引用

Jisuanji Xuebao/Chinese Journal of Computers 2023年第4期46卷 671-689页

作者： Guo, Dan Yao, Shen-Tao Wang, Hui Wang, Meng School of Computer and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230094 China Key Laboratory of Knowledge Engineering with Big Data（Hefei University of Technology） Ministry of Education Hefei230601 China Intelligent Interconnected Systems Laboratory of Anhui Province（Hefei University of Technology） Hefei230601 China

Video question answering（VideoQA）is a typical cross-modal understanding task. Its challenge lies in how to learn appropriate multimodal representation and cross-modal correlation for answer inference. Most existing video question answering methods focus on the latter，e. g.，relationship learning between each video frame or clip and word. In this work， we devote to advanced feature embedding of both video and query. We develop a clustering-based VLAD technique for VideoQA. The novelty of our work is the joint exploitation of temporal aggregation and correlation in multimodality. We propose an end-to-end trainable Transformed VLAD embedding network， named TVLAD-Net. TVLAD-Net constructs a differentiable aggregation network module（i. e.， convolutional Residual-less VLAD Block）to generate compact VLAD descriptors（transforming N frames，clips or words to compact K descriptors while K © 2023 Science Press. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RGB-D Visual Odometry Based on Semantic Feature Points in Dynamic Environments 1st

RGB-D Visual Odometry Based on Semantic Feature Points in ...

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Wang, Hao Wang, Yincan Fang, Baofu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Anhui230009 China School of Computer Science and Information Engineering HeFei University of Technology Anhui Hefei230009 China

ISBN: (纸本)9783030930486

Various algorithms of traditional visual Simultaneous Localization and Mapping (SLAM) can well match with static scenes, but mismatches will occur in dynamic scenes, which makes the positioning and mapping of the SLAM system produce large errors. Therefore, this paper proposed a visual odometry algorithm based on semantic feature points, which can improve the positioning accuracy in dynamic scenes. The algorithm combined semantic information to detect dynamic objects, and then detects and eliminates dynamic feature points. This paper conducted an extensive evaluation of the system and compared it with ORB-SLAM3 and other dynamic scene SLAM systems. The experimental results show that this method greatly improves the positioning accuracy of the camera and the robustness of the system in a highly complex dynamic environment, which verifies the advancement and effectiveness of the algorithm in this paper. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Scene-Adaptive Person Search via Bilateral Modulations

arXiv

引用

arXiv 2024年

作者： Jiang, Yimin Wang, Huibing Peng, Jinjia Fu, Xianping Wang, Yang School of Information Science and Technology Dalian Maritime University Dalian China School of Cyber Security and Computer Hebei University Baoding China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei China

Person search aims to localize specific a target person from a gallery set of images with various scenes. As the scene of moving pedestrian changes, the captured person image inevitably bring in lots of background noise and foreground noise on the person feature, which are completely unrelated to the person identity, leading to severe performance degeneration. To address this issue, we present a Scene-Adaptive Person Search (SEAS) model by introducing bilateral modulations to simultaneously eliminate scene noise and maintain a consistent person representation to adapt to various scenes. In SEAS, a Background Modulation Network (BMN) is designed to encode the feature extracted from the detected bounding box into a multi-granularity embedding, which reduces the input of background noise from multiple levels with norm-aware. Additionally, to mitigate the effect of foreground noise on the person feature, SEAS introduces a Foreground Modulation Network (FMN) to compute the clutter reduction offset for the person embedding based on the feature map of the scene image. By bilateral modulations on both background and foreground within an end-to-end manner, SEAS obtains consistent feature representations without scene noise. SEAS can achieve state-of-the-art (SOTA) performance on two benchmark datasets, CUHK-SYSU with 97.1% mAP and PRW with 60.5% mAP. The code is available at https://***/whbdmu/SEAS. © 2024, CC0.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

An Efficient Customized Blockchain System for Inter-Organizational Processes

An Efficient Customized Blockchain System for Inter-Organiza...

引用

IEEE International Conference on Web Services (ICWS)

作者： Puwei Wang Zhouxing Sun Rui Li Jinchuan Chen Ping Gong Xiaoyong Du School of Information Renmin University of China Key Laboratory of Data Engineering and Knowledge Engineering (Ministry of Education) Renmin University of China School of Mathematics Renmin University of China College of Computer and Cyber Security Fujian Normal University

Blockchain technologies pave a promising way for implementing the inter-organizational processes. Most of the current research works translate the execution logic in the process models into the smart contracts, which can run independently on the blockchain without the outside process engine. However, the works usually suffer from the execution and storage costs, since the translation needs to be done when the processes are deployed. In this paper, we customize a process engine for executing the inter-organizational business processes via a blockchain-style procedure, i.e., checking the validity of transactions, adding the valid transactions into the blockchain through the consensus mechanism, and then updating the process states according to the committed transactions. And then, we build a blockchain system by embedding the customized process engine into the blockchain nodes. Moreover, in order to realize the interactions between the inter-organizational processes running on blockchain and the services outside blockchain, we propose a blockchain-based approach for service registration, binding and invocation, and design a lease-based concurrency control protocol to logically isolate transactions from each other when invoking the services simultaneously. Finally, we implement a prototype system based on a permissioned blockchain platform Hyperledger Fabric and a process engine Activiti. The experimental results show the proposed blockchain system can execute the inter-organizational processes correctly and efficiently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Zero-shot Learning Method with a Multi-Modal knowledge Graph

A Zero-shot Learning Method with a Multi-Modal Knowledge Gra...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Yuhong Zhang Haitao Shu Chenyang Bu Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Zero-shot learning aims to recognize unseen-classes using some seen-class samples as training set. It is challenging owing to that the feature representations of unseen-class samples are unavailable. Existing methods transfer the mapping from seen-classes to unseen-classes with the correlation as a bridge, in which, the semantic representations are used to discriminate the classes. However, the unavailability of visual representations for unseen-classes and the insufficient discrimination of semantic representations make the zero-shot learning challenging. Therefore, the visual representations are learned as complements to semantic representations to construct a multi-modal knowledge graph (KG), and a zero-shot learning method based on multi-modal KG is proposed in this paper. Specially, a semantic KG is introduced to capture the correlation of classes, and with the correlation, the visual feature representations of all classes are learned. Then, the discriminative visual representations and the semantic representations are used together to construct a multi-modal KG. With the multi-modal KG, the classifier for seen-classes is transferred to unseen classes. Extensive experimental results show the effectiveness of our method.

关键词： Learning systems Representation learning Training Bridges Visualization Correlation Semantics

来源：评论

学校读者我要写书评

暂无评论

Learning Group-Disentangled Representation for Interpretable Thoracic Pathologic Prediction

Learning Group-Disentangled Representation for Interpretable...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Li, Hao Wu, Yirui Hu, Hexuan Lu, Hu Lai, Yong Wan, Shaohua Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources China College of Computer and Information Hohai University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China School of Computer Science and Communication Engineering Jiangsu University China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China

ISBN: (纸本)9781665468190

Deep learning methods have shown significant performance in medical image analysis tasks. However, they generally act like 'black box' without explanations in both feature extraction and decision processes, leading to lack of clinical insights and high risk assessments. To aid deep learning in envisioning diseases with visual clues, we propose Representation Group-Disentangling Network (RGD-Net), which can completely disentangle feature space of input X-ray images into several independent feature groups, each corresponding to a specific disease. Taking several semantically related and labeled X-ray images as input, RGD-Net firstly extracts completely group-disentangled representations of diseases through Group-Disentangle Module, which applies group-swap and linking operations to construct latent space by enforcing semantic consistency of attributes. To prevent learning degenerate representations defined as shortcut problem, we further introduce adversarial constricts on mapping from features to diseases, thus avoiding model collapse with former free-form disentanglement. Experiments on chestxray-14 and ChestXpert datasets demonstrate that RGD-Net are effective in predicting diseases with remarkable advantages, which leverage potential factors contributing to different diseases, thus enhancing interpretability in working patterns of deep learning methods. © 2022 IEEE.

关键词： Forecasting

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：