9 results on '"Wei, Zhihui"'
Search Results
2. MCF-YOLOv5: A Small Target Detection Algorithm Based on Multi-Scale Feature Fusion Improved YOLOv5.
- Author
-
Gao, Song, Gao, Mingwang, and Wei, Zhihui
- Subjects
OBJECT recognition (Computer vision) ,ALGORITHMS ,DATA augmentation ,COMPUTATIONAL complexity ,FEATURE extraction ,DEEP learning - Abstract
In recent years, many deep learning-based object detection methods have performed well in various applications, especially in large-scale object detection. However, when detecting small targets, previous object detection algorithms cannot achieve good results due to the characteristics of the small targets themselves. To address the aforementioned issues, we propose the small object algorithm model MCF-YOLOv5, which has undergone three improvements based on YOLOv5. Firstly, a data augmentation strategy combining Mixup and Mosaic is used to increase the number of small targets in the image and reduce the interference of noise and changes in detection. Secondly, in order to accurately locate the position of small targets and reduce the impact of unimportant information on small targets in the image, the attention mechanism coordinate attention is introduced in YOLOv5's neck network. Finally, we improve the Feature Pyramid Network (FPN) structure and add a small object detection layer to enhance the feature extraction ability of small objects and improve the detection accuracy of small objects. The experimental results show that, with a small increase in computational complexity, the proposed MCF-YOLOv5 achieves better performance than the baseline on both the VisDrone2021 dataset and the Tsinghua Tencent100K dataset. Compared with YOLOv5, MCF-YOLOv5 has improved detection AP
small by 3.3% and 3.6%, respectively. [ABSTRACT FROM AUTHOR]- Published
- 2024
- Full Text
- View/download PDF
3. Unsupervised Low-Light Image Enhancement in the Fourier Transform Domain.
- Author
-
Ming, Feng, Wei, Zhihui, and Zhang, Jun
- Subjects
IMAGE intensifiers ,COMPUTER vision ,SEPARATION of variables - Abstract
Low-light image enhancement is an important task in computer vision. Deep learning-based low-light image enhancement has made significant progress. But the current methods also face the challenge of relying on a wide variety of low-light/normal-light paired images and amplifying noise while enhancing brightness. Based on existing experimental observation that most luminance information concentrates on amplitudes while noise is closely related to phases, an unsupervised low-light image enhancement method in the Fourier transform domain is proposed. In our method, the low-light image is firstly transformed into the amplitude component and phase component via Fourier transform. The luminance of low-light image is enhanced by CycleGAN in the amplitude domain, and the phase component is denoising. The cycle consistency losses both in the Fourier transform domain and spatial domain are used in training. The proposed method has been validated on publicly available test sets and shows that our method achieves superior results than other approaches in low-light image enhancement and noise suppression. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Multiscale Alternately Updated Clique Network for Hyperspectral Image Classification.
- Author
-
Liu, Qian, Wu, Zebin, Du, Qian, Xu, Yang, and Wei, Zhihui
- Subjects
DEEP learning ,CLASSIFICATION ,INFORMATION networks - Abstract
Recently, deep learning has drawn significant attention in hyperspectral image (HSI) classification. With the growth of network depth and feature integration, deep learning demands abundant labeled samples to optimize many parameters. Unfortunately, most hyperspectral data are unlabeled and the available labeled samples are extremely limited. How to obtain richer features under limited training samples is a challenge for HSI classification. To tackle this issue, a new supervised multiscale alternately updated clique network (MSCN) is proposed for HSI classification to fully employ HSI features in different scales. Based on the Clique Block, we design the multiscale alternately updated clique block (MSCB) that applies convolution kernels of various sizes to adaptively exploit the multiscale HSI information and merge them within the block. Meanwhile, the recurrent feedback architecture is introduced to reuse high-level visual information and network parameters. The proposed MSCN includes two MSCBs to capture the multiscale spectral and spatial information in turn. The MSCN improves the information flow and the efficiency of parameter tuning through the feedback mechanism and the cross-utilization of multiscale feature. It not only obtains more abstract HSI information, but also reduces the network depth and the number of parameters, thereby improving the classification accuracy under limited samples. To certify the validity of the proposed MSCN, experiments are conducted on three real HSI datasets and compared with multiple state-of-the-art deep learning-based approaches. The experimental results demonstrate that the presented multiscale network achieves superior performance, especially in the case of a small number of training samples. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
5. CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification.
- Author
-
Liu, Qichao, Xiao, Liang, Yang, Jingxiang, and Wei, Zhihui
- Subjects
IMAGE fusion ,CONVOLUTIONAL neural networks ,WEIGHT training ,CLASSIFICATION ,LAND cover - Abstract
Recently, the graph convolutional network (GCN) has drawn increasing attention in the hyperspectral image (HSI) classification. Compared with the convolutional neural network (CNN) with fixed square kernels, GCN can explicitly utilize the correlation between adjacent land covers and conduct flexible convolution on arbitrarily irregular image regions; hence, the HSI spatial contextual structure can be better modeled. However, to reduce the computational complexity and promote the semantic structure learning of land covers, GCN usually works on superpixel-based nodes rather than pixel-based nodes; thus, the pixel-level spectral–spatial features cannot be captured. To fully leverage the advantages of the CNN and GCN, we propose a heterogeneous deep network called CNN-enhanced GCN (CEGCN), in which CNN and GCN branches perform feature learning on small-scale regular regions and large-scale irregular regions, and generate complementary spectral–spatial features at pixel and superpixel levels, respectively. To alleviate the structural incompatibility of the data representation between the Euclidean data-oriented CNN and non-Euclidean data-oriented GCN, we propose the graph encoder and decoder to propagate features between image pixels and graph nodes, thus enabling the CNN and GCN to collaborate in a single network. In contrast to other GCN-based methods that encode HSI into a graph during preprocessing, we integrate the graph encoding process into the network and learn edge weights from training data, which can promote the node feature learning and make the graph more adaptive to HSI content. Extensive experiments on three data sets demonstrate that the proposed CEGCN is both qualitatively and quantitatively competitive compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
6. Multi-parameter deep-perception and many-objective autonomous-control of rolling schedule on high speed cold tandem mill.
- Author
-
Hu, Ziyu, Wei, Zhihui, Ma, Xuemin, Sun, Hao, and Yang, Jingming
- Subjects
PROCESS control systems ,GAUSSIAN mixture models ,REAL-time control ,EVOLUTIONARY algorithms ,DEPTH perception ,CALORIC expenditure - Abstract
High-speed cold tandem rolling process control system consists of complex mechanical and electrical equipments. The coupling association of these equipments makes multi-objective rolling process complicated to be predicted and controlled. In order to achieve higher prediction precision, a multi-parameter depth perception model is established based on a deep belief network. To get higher control precision in real time, a multi-objective rolling optimization method is introduced, which is supported by many-objective evolutionary algorithm. Five objectives are selected as rolling schedule optimization objective: equal relative power margin, slippage prevent, good flatness, total energy consumption and energy consumption per ton. Simulation results show that many-objective evolutionary algorithm based on decomposition and Gaussian mixture model achieves a set of balance solutions on these objectives. The proposed method could not only predict rolling force and rolling power in real time, but also give the solutions for many-objective reduction schedule. • The relationships between different control variables and optimization objectives are analyzed. • The model combined deep learning network and mechanism model is used to improve the prediction of rolling parameter. • Tension and speed, which effect rolling power and quality, are considered for rolling schedule. • Many-objective evolutionary algorithm is employed to optimize rolling schedule. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
7. From Local to Global: Class Feature Fused Fully Convolutional Network for Hyperspectral Image Classification.
- Author
-
Liu, Qian, Wu, Zebin, Jia, Xiuping, Xu, Yang, and Wei, Zhihui
- Subjects
DEEP learning ,DATA mining ,FEATURE extraction ,CLASSIFICATION ,INFORMATION networks - Abstract
Current mainstream networks for hyperspectral image (HSI) classification employ image patches as inputs for feature extraction. Spatial information extraction is limited by the size of inputs, which makes networks unable to perform effective learning and reasoning from the global perspective. As a common component for capturing long-range dependencies, non-local networks with pixel-by-pixel information interaction bring unaffordable computational costs and information redundancy. To address the above issues, we propose a class feature fused fully convolutional network (CFF-FCN) with a local feature extraction block (LFEB) and a class feature fusion block (CFFB) to jointly utilize local and global information. LFEB based on dilated convolutions and reverse loop mechanism can acquire the local spectral–spatial features at multiple levels and deliver shallower layer features for coarse classification. CFFB calculates global class representation to enhance pixel features. Robust global information is propagated to every pixel with low computational cost. CFF-FCN considers a fully global class context and obtains more discriminative representation by concatenating high-level local features and re-integrated global features. Experimental results conducted on three real HSI data sets demonstrate that the proposed fully convolutional network is superior to multiple state-of-the-art deep learning-based approaches, especially in the case of a small number of training samples. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
8. A Lightweight Spectral–Spatial Feature Extraction and Fusion Network for Hyperspectral Image Classification.
- Author
-
Chen, Linlin, Wei, Zhihui, and Xu, Yang
- Subjects
- *
FEATURE extraction , *CONVOLUTIONAL neural networks , *DEEP learning , *CLASSIFICATION - Abstract
Hyperspectral image (HSI) classification accuracy has been greatly improved by employing deep learning. The current research mainly focuses on how to build a deep network to improve the accuracy. However, these networks tend to be more complex and have more parameters, which makes the model difficult to train and easy to overfit. Therefore, we present a lightweight deep convolutional neural network (CNN) model called S2FEF-CNN. In this model, three S2FEF blocks are used for the joint spectral–spatial features extraction. Each S2FEF block uses 1D spectral convolution to extract spectral features and 2D spatial convolution to extract spatial features, respectively, and then fuses spectral and spatial features by multiplication. Instead of using the full connected layer, two pooling layers follow three blocks for dimension reduction, which further reduces the training parameters. We compared our method with some state-of-the-art HSI classification methods based on deep network on three commonly used hyperspectral datasets. The results show that our network can achieve a comparable classification accuracy with significantly reduced parameters compared to the above deep networks, which reflects its potential advantages in HSI classification. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
9. Symmetrical irregular local features for fine-grained visual classification.
- Author
-
Yang, Ming, Xu, Yang, Wu, Zebin, and Wei, Zhihui
- Subjects
- *
FEATURE extraction , *GEOMETRIC shapes , *CLASSIFICATION , *DEEP learning - Abstract
Fine-grained visual classification (FGVC) has small inter-class variations and large intra-class variations, therefore, recognizing sub-classes belonging to the same meta-class is a difficult task. Recent studies have primarily addressed this problem by locating the most discriminative image regions, and the extracted image regions have been used to improve the ability to capture subtle differences. Most of these studies used regular anchors to extract local features. However, the local features of the target are mostly irregular geometric shapes. These methods cannot fully extract the features and inevitably include a large amount of irrelevant information, resulting in reduced credibility of the evaluation results. However, the spatial relationship between the features is easily overlooked. This study proposes a novel local feature extraction anchor generator (LFEAG) to simulate the shapes of irregular features. Thus, discriminative features can be fully included in the extracted features. In addition, an effective symmetrized local feature extraction module (SLFEM) based on an attention mechanism is proposed to fully use the spatial relationship between the extracted local features and highlight discriminative features. Experiments on six popular fine-grained benchmark datasets: CUB-200-2011, Stanford Dogs, Food-101, Oxford-IIIT Pets, Aircraft and NA-Birds, are conducted to demonstrate the advantages of our proposed method. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.