Query:
学者姓名:杨金福
Refining:
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract :
Channel pruning can reduce the number of neural network parameters and computational cost by eliminating redundant channels, its main purpose is to adapt to resource constrained devices. Evaluation-based global pruning and network search-based pruning are two common methods of channel pruning. However, the network architecture pruned by the global mask is often not optimal, while the method that directly searches for the optimal architecture will introduce a large number of hyperparameters, which greatly increases the training cost. In this paper, we propose a novel Two-dimensional information Entropy based Channel Pruning method (TECP). The pruning process consists of two steps. First, a global mask pruning scheme is employed to obtained a pre-pruning model. Then, the two-dimensional information entropy is calculated by using feature maps of dense network to adjust the pre-pruning model adaptively to get a compact network. Moreover, the entropy values are used to determine the minimum number of reserved channels per layer based on to avoid the imbalance of network architecture and the layer collapse caused by global pruning. Extensive experiments with a variety of networks on several datasets clearly demonstrate the effectiveness of our proposed TECP method. For example, results show that on CIFAR-10, the compressed model achieves comparable accuracy to the original model, but with a significantly lower number of parameters (44.29% for ResNet-20 and 46.79% for VGG-16). This is beneficial for industrial deployment. And experimental results also show that TECP method obtain the better performance compared with state-of-the-art method.
Keyword :
Network architecture Network architecture Two-dimensional information entropy Two-dimensional information entropy Channel pruning Channel pruning Feature map Feature map
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Xu, Yifei , Yang, Jinfu , Wang, Runshi et al. An effective two-stage channel pruning method based on two-dimensional information entropy [J]. | APPLIED INTELLIGENCE , 2024 , 54 (17-18) : 8491-8504 . |
MLA | Xu, Yifei et al. "An effective two-stage channel pruning method based on two-dimensional information entropy" . | APPLIED INTELLIGENCE 54 . 17-18 (2024) : 8491-8504 . |
APA | Xu, Yifei , Yang, Jinfu , Wang, Runshi , Li, Haoqing . An effective two-stage channel pruning method based on two-dimensional information entropy . | APPLIED INTELLIGENCE , 2024 , 54 (17-18) , 8491-8504 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Few-shot classification aims to classify samples with a limited quantity of labeled training data, and it can be widely applied in practical scenarios such as wastewater treatment plants and healthcare. Compared with traditional methods, existing deep metric-based algorithms have excelled in few-shot classification tasks, but some issues need to be further investigated. While current standard convolutional networks can extract expressive depth features, they do not fully exploit the relationships among input sample attributes. Two problems are included here: (1) how to extract more expressive features and transform them into attributes, and (2) how to obtain the optimal combination of sample class attributes. This paper proposes a few-shot classification method based on manifold metric learning (MML) with feature space embedded in symmetric positive definite (SPD) manifolds to overcome the above limitations. First, significant features are extracted using the proposed joint dynamic convolution module. Second, the definition and properties of Riemannian popular strictly convex geodesics are used to minimize the proposed MML loss function and obtain the optimal attribute correlation matrix A. We theoretically prove that the MML is popularly strictly convex in the SPD and obtain the global optimal solution in the closed space. Extensive experimental results on popular datasets show that our proposed approach outperforms other state-of-the-art methods.
Keyword :
dynamic convolution dynamic convolution metric learning metric learning few-shot classification few-shot classification symmetric positive definite manifold symmetric positive definite manifold
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Shang, Qingzhen , Yang, Jinfu , Ma, Jiaqi et al. Few-shot classification based on manifold metric learning [J]. | JOURNAL OF ELECTRONIC IMAGING , 2024 , 33 (1) . |
MLA | Shang, Qingzhen et al. "Few-shot classification based on manifold metric learning" . | JOURNAL OF ELECTRONIC IMAGING 33 . 1 (2024) . |
APA | Shang, Qingzhen , Yang, Jinfu , Ma, Jiaqi , Zhang, Jiahui . Few-shot classification based on manifold metric learning . | JOURNAL OF ELECTRONIC IMAGING , 2024 , 33 (1) . |
Export to | NoteExpress RIS BibTex |
Abstract :
Structural geometry constraints, such as perpendicularity, parallelism and coplanarity, are widely existing in man-made scene, especially in Manhattan scene. By fully exploiting these structural properties, we propose a monocular visual-inertial odometry (VIO) using point and line features with structural constraints. First, a coarse-to-fine vanishing points estimation method with line segment consistency verification is presented to classify lines into structural and non-structural lines accurately with less computation cost. Then, to get precise estimation of camera pose and the position of 3D landmarks, a cost function which combines structural line constraints with feature reprojection residual and inertial measurement unit residual is minimized under a sliding window framework. For geometric representation of lines, Plucker coordinates and orthonormal representation are utilized for 3D line transformation and non-linear optimization respectively. Sufficient evaluations are conducted using two public datasets to verify that the proposed system can effectively enhance the localization accuracy and robustness than other existing state-of-the-art VIO systems with acceptable time consumption.
Keyword :
Structural line Structural line Vanishing point Vanishing point Structural constraints Structural constraints Visual-inertial odometry Visual-inertial odometry
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Zhang, Jiahui , Yang, Jinfu , Ma, Jiaqi . Monocular visual-inertial odometry leveraging point-line features with structural constraints [J]. | VISUAL COMPUTER , 2023 , 40 (2) : 647-661 . |
MLA | Zhang, Jiahui et al. "Monocular visual-inertial odometry leveraging point-line features with structural constraints" . | VISUAL COMPUTER 40 . 2 (2023) : 647-661 . |
APA | Zhang, Jiahui , Yang, Jinfu , Ma, Jiaqi . Monocular visual-inertial odometry leveraging point-line features with structural constraints . | VISUAL COMPUTER , 2023 , 40 (2) , 647-661 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Visual simultaneous localization and mapping (VSLAM) is one of the foremost principal technologies for intelligent robots to implement environment perception. Many research works have focused on proposing comprehensive and integrated systems based on the static environment assumption. However, the elements whose motion status changes frequently, namely short-term dynamic elements, can significantly affect the system performance. Therefore, it is extremely momentous to cope with short-term dynamic elements to make the VSLAM system more adaptable to dynamic scenes. This paper proposes a coarse-to-fine elimination strategy for short-term dynamic elements based on motion status check (MSC) and feature points update (FPU). First, an object detection module is designed to obtain semantic information and screen out the potential short-term dynamic elements. And then an MSC module is proposed to judge the true status of these elements and thus ultimately determine whether to eliminate them. In addition, an FPU module is introduced to update the extracted feature points according to calculating the dynamic region factor to improve the robustness of VSLAM system. Quantitative and qualitative experiments on two challenging public datasets are performed. The results demonstrate that our method effectively eliminates the influence of short-term dynamic elements and outperforms other state-of-the-art methods. (c) 2022 SPIE and IS&T
Keyword :
visual simultaneous localization and mapping visual simultaneous localization and mapping motion status check motion status check short-term dynamic elements short-term dynamic elements feature points update feature points update coarse-to-fine coarse-to-fine
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Fu, Fuji , Yang, Jinfu , Zhang, Jiahui et al. Eliminating short-term dynamic elements for robust visual simultaneous localization and mapping using a coarse-to-fine strategy [J]. | JOURNAL OF ELECTRONIC IMAGING , 2022 , 31 (5) . |
MLA | Fu, Fuji et al. "Eliminating short-term dynamic elements for robust visual simultaneous localization and mapping using a coarse-to-fine strategy" . | JOURNAL OF ELECTRONIC IMAGING 31 . 5 (2022) . |
APA | Fu, Fuji , Yang, Jinfu , Zhang, Jiahui , Ma, Jiaqi . Eliminating short-term dynamic elements for robust visual simultaneous localization and mapping using a coarse-to-fine strategy . | JOURNAL OF ELECTRONIC IMAGING , 2022 , 31 (5) . |
Export to | NoteExpress RIS BibTex |
Abstract :
With the continuous development of video acquisition equipment and technology, the number of videos has grown rapidly. It is a challenging task in video retrieval to find target video moments accurately in massive videos. Cross-modal video moment retrieval is to find a moment matching the query from the video database. Existing works focus mostly on matching the text with the moment, while ignoring the context content in the adjacent moment. As a result, there exists the problem of insufficient expression of feature relation. In this paper, a novel moment retrieval network is proposed, which highlights the significant features through residual channel attention. At the same time, a temporal adjacent network is designed to capture the context information of the adjacent moment. Experimental results show that the proposed method achieves better performance than the mainstream candidate matching based and video- text features relation based methods.
Keyword :
Temporal adjacent network Temporal adjacent network Feature relationship Feature relationship Cross-modal video moment retrieval Cross-modal video moment retrieval Residual channel attention Residual channel attention
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Yang Jinfu , Liu Yubin , Song Lin et al. Cross-modal Video Moment Retrieval Based on Enhancing Significant Features [J]. | JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY , 2022 , 44 (12) : 4395-4404 . |
MLA | Yang Jinfu et al. "Cross-modal Video Moment Retrieval Based on Enhancing Significant Features" . | JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY 44 . 12 (2022) : 4395-4404 . |
APA | Yang Jinfu , Liu Yubin , Song Lin , Yan Xue . Cross-modal Video Moment Retrieval Based on Enhancing Significant Features . | JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY , 2022 , 44 (12) , 4395-4404 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Face detection has achieved tremendous strides thanks to convolutional neural networks. However, dense face detection remains an open challenge due to large face scale variation, tiny faces, and serious occlusion. This paper presents a robust, dense face detector using global context and visual attention mechanisms which can significantly improve detection accuracy. Specifically, a global context fusion module with top-down feedback is proposed to improve the ability to identify tiny faces. Moreover, a visual attention mechanism is employed to solve the problem of occlusion. Experimental results on the public face datasets WIDER FACE and FDDB demonstrate the effectiveness of the proposed method.
Keyword :
Face detection Face detection global context global context deep learning deep learning computer vision computer vision attention mechanism attention mechanism
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Song, Lin , Yang, Jin-Fu , Shang, Qing-Zhen et al. Dense Face Network: A Dense Face Detector Based on Global Context and Visual Attention Mechanism [J]. | MACHINE INTELLIGENCE RESEARCH , 2022 , 19 (3) : 247-256 . |
MLA | Song, Lin et al. "Dense Face Network: A Dense Face Detector Based on Global Context and Visual Attention Mechanism" . | MACHINE INTELLIGENCE RESEARCH 19 . 3 (2022) : 247-256 . |
APA | Song, Lin , Yang, Jin-Fu , Shang, Qing-Zhen , Li, Ming-Ai . Dense Face Network: A Dense Face Detector Based on Global Context and Visual Attention Mechanism . | MACHINE INTELLIGENCE RESEARCH , 2022 , 19 (3) , 247-256 . |
Export to | NoteExpress RIS BibTex |
Abstract :
The goal of pedestrian trajectory prediction is to predict the future trajectory according to the historical one of pedestrians. Multimodal information in the historical trajectory is conducive to perception and positioning, especially visual information and position coordinates. However, most of the current algorithms ignore the significance of multimodal information in the historical trajectory. We describe pedestrian trajectory prediction as a multimodal problem, in which historical trajectory is divided into an image and coordinate information. Specifically, we apply fully connected long short-term memory (FC-LSTM) and convolutional LSTM (ConvLSTM) to receive and process location coordinates and visual information respectively, and then fuse the information by a multimodal fusion module. Then, the attention pyramid social interaction module is built based on information fusion, to reason complex spatial and social relations between target and neighbors adaptively. The proposed approach is validated on different experimental verification tasks on which it can get better performance in terms of accuracy than other counterparts. (c) 2022 SPIE and IS&T
Keyword :
trajectory prediction trajectory prediction recurrent neural network recurrent neural network multimodal fusion multimodal fusion attention mechanism attention mechanism
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Yan, Xue , Yang, Jinfu , Liu, Yubin et al. Multimodal based attention-pyramid for predicting pedestrian trajectory [J]. | JOURNAL OF ELECTRONIC IMAGING , 2022 , 31 (5) . |
MLA | Yan, Xue et al. "Multimodal based attention-pyramid for predicting pedestrian trajectory" . | JOURNAL OF ELECTRONIC IMAGING 31 . 5 (2022) . |
APA | Yan, Xue , Yang, Jinfu , Liu, Yubin , Song, Lin . Multimodal based attention-pyramid for predicting pedestrian trajectory . | JOURNAL OF ELECTRONIC IMAGING , 2022 , 31 (5) . |
Export to | NoteExpress RIS BibTex |
Abstract :
随着高校实验学科发展和研究范围的不断扩大,使用的危险化学品种类和数量逐年增多,如何实现危险化学品的安全管理已成为高校实验室安全管理工作的重要内容.在当前国家大力倡导平安校园建设的背景下,通过分析高校实验室危险化学品管理工作的现状及存在的问题,提出了加强危险化学品管理的建议和对策,探索出一套对危险化学品进行全过程监管的体系,为提高高校实验室危险化学品管理水平提供借鉴.
Keyword :
实验室安全 实验室安全 全过程监管 全过程监管 危险化学品 危险化学品
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 何淼 , 赵明 , 韩光宇 et al. 高校实验室危险化学品管理现状与全过程监管实践 [J]. | 实验室研究与探索 , 2021 , 40 (3) : 297-300 . |
MLA | 何淼 et al. "高校实验室危险化学品管理现状与全过程监管实践" . | 实验室研究与探索 40 . 3 (2021) : 297-300 . |
APA | 何淼 , 赵明 , 韩光宇 , 杨金福 . 高校实验室危险化学品管理现状与全过程监管实践 . | 实验室研究与探索 , 2021 , 40 (3) , 297-300 . |
Export to | NoteExpress RIS BibTex |
Abstract :
危险化学品的管理已经成为高校实验室安全管理的重点,对危险化学品的采购、储存、使用、处置、安全教育等环节的全周期管理日趋重要.结合北京工业大学两年的化学品采购管理平台实践应用经验,探讨并实施了实验室危险化学品全周期信息化管理,为实验室在危险化学品管理方面信息化建设的优化提供案例支撑.
Keyword :
危险化学品 危险化学品 全周期 全周期 信息化管理 信息化管理
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 韩光宇 , 何淼 , 赵明 et al. 高校实验室危险化学品全周期信息化管理实践与探索 [J]. | 实验技术与管理 , 2021 , 38 (6) : 278-281 . |
MLA | 韩光宇 et al. "高校实验室危险化学品全周期信息化管理实践与探索" . | 实验技术与管理 38 . 6 (2021) : 278-281 . |
APA | 韩光宇 , 何淼 , 赵明 , 杨金福 . 高校实验室危险化学品全周期信息化管理实践与探索 . | 实验技术与管理 , 2021 , 38 (6) , 278-281 . |
Export to | NoteExpress RIS BibTex |
Abstract :
高校实验室危险化学品管理现状与全过程监管实践
Keyword :
危险化学品 危险化学品 实验室安全 实验室安全 全过程监管 全过程监管
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 何淼 , 赵明 , 韩光宇 et al. 高校实验室危险化学品管理现状与全过程监管实践 [J]. | 何淼 , 2021 , 40 (3) : 297-300 . |
MLA | 何淼 et al. "高校实验室危险化学品管理现状与全过程监管实践" . | 何淼 40 . 3 (2021) : 297-300 . |
APA | 何淼 , 赵明 , 韩光宇 , 杨金福 , 实验室研究与探索 . 高校实验室危险化学品管理现状与全过程监管实践 . | 何淼 , 2021 , 40 (3) , 297-300 . |
Export to | NoteExpress RIS BibTex |
Export
Results: |
Selected to |
Format: |