Article
Computer Science, Artificial Intelligence
Dan Zhang, Pan Li, Lei Zhao, Duanqing Xu, Dongming Lu
Summary: In this paper, a convolutional neural network for image denoising is proposed, which includes noise mapping block, texture compensation block, and composition block. The model achieves superior performance by learning noise mapping, enhancing details, and synthesizing outputs.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Qi Zhang, Jingyu Xiao, Chunwei Tian, Jiayu Xu, Shichao Zhang, Chia-Wen Lin
Summary: This paper proposes a parallel and serial denoising network (PSDNet) for image denoising to preserve image texture. The proposed PSDNet contains a parallel block (PB), a serial block (SB), and a reconstruction block (RB), which achieve effective denoising results through the use of heterogeneous sub-networks, an enhanced residual dense architecture, and reconstruction techniques.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Shengqin Bian, Xinyu He, Zhengguang Xu, Lixin Zhang
Summary: In this paper, a hybrid dilated convolution-based denoising network (AMDNet) incorporating attention mechanisms is proposed to address the issue of weak influence of shallow layers on deep layers in complex denoising tasks. Experimental results demonstrate the outstanding performance of AMDNet on various tasks.
Article
Computer Science, Artificial Intelligence
Vedat Acar, Ender M. Eksioglu
Summary: Image denoising is a crucial problem in image processing, aiming to suppress noise while preserving the textures. In this paper, a novel method called Densely connected Dilated Residual Network (DDR-Net) is proposed, which combines dense and residual blocks with dilated convolutions to extract multi-scale information and prevent information loss.
NEURAL PROCESSING LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Xinlei Jia, Yali Peng, Bao Ge, Jun Li, Shigang Liu, Wenan Wang
Summary: In this paper, a new image denoising method called multi-scale dilated residual convolution network (MDRN) is proposed. This method effectively extracts multi-scale information from images and recovers image details. Experimental results demonstrate that MDRN outperforms state-of-the-art denoising methods on both synthetic and real-world noisy images.
NEURAL PROCESSING LETTERS
(2023)
Article
Computer Science, Information Systems
Su Li, Bowen Fu, Jiangdong Wei, Yunfei Lv, Qingnan Wang, Jihui Tu
Summary: A novel end-to-end denoising model (ULNet) based on CNN and feature attention is proposed to remove noise from ultrasonic logging images effectively. The model integrates global and local features, uses feature attention to distinguish channel feature weights, and shows potential for practical denoising of ultrasonic logging images in selected study datasets.
Article
Computer Science, Artificial Intelligence
Chunwei Tian, Menghua Zheng, Wangmeng Zuo, Bob Zhang, Yanning Zhang, David Zhang
Summary: This paper proposes a multi-stage image denoising CNN with wavelet transform, using dynamic convolution, wavelet transform and enhancement, and residual block to improve denoising performance. Experimental results show that the proposed method outperforms popular denoising methods.
PATTERN RECOGNITION
(2023)
Article
Engineering, Electrical & Electronic
Zhiyu Lyu, Yan Chen, Yimin Hou, Chengkun Zhang
Summary: This paper proposes a novel network called NSTBNet, which integrates nonsubsampled shearlet transform (NSST) and a broad convolutional neural network. It has the ability to handle different noise levels and spatially variant AWGN, achieving a good trade-off between denoising performance and detail preservation.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Computer Science, Software Engineering
Xiaoben Jiang, Yan Jin, Yu Yao
Summary: This study proposes a low-dose CT denoising model based on multiscale parallel convolution neural network, which utilizes residual learning and batch normalization to improve visual effect, and introduces dilated convolution and multiscale parallel method to extract multiscale detail features.
Article
Instruments & Instrumentation
Jia Lina, He Xu, Huang Aimin, Jia Beibei, Gui Zhiguo
Summary: This study proposes a dual edge extraction multi-scale attention mechanism convolution neural network (DEMACNN) based on a compound loss to improve the quality of LDCT images. The network extracts edge information using edge extraction operators from both the input images and the feature maps, enhances effective information using attention mechanism and multi-scale module, and applies the residual learning method to improve network performance. A compound loss function is also proposed to enhance the denoising ability of the network and retain image edges.
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY
(2023)
Article
Instruments & Instrumentation
Chao Tu, Wanjun Liu, Wentao Jiang, Linlin Zhao
Summary: The approach based on Convolutional Neural Network model has been widely used in hyperspectral image classification, but it has limitations in extracting features and considering spatial-spectral distribution. To address these issues, we propose a method called RDDC-3DCNN that incorporates residual dense and dilated convolutions. This method achieves better classification performance compared to advanced algorithms.
INFRARED PHYSICS & TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Shaodong Xie, Jiagang Song, Yuxuan Hu, Chengyuan Zhang, Shichao Zhang
Summary: In this paper, a multi-level information fusion CNN (MLIFCNN) is proposed for image denoising. It combines different modules such as fine information extraction, multi-level information interaction, and coarse information refinement to extract effective information and achieve good denoising results in complex backgrounds.
Article
Computer Science, Software Engineering
Wanping Liu, Yueyue Li, Dong Huang
Summary: Due to the rapid advancement of GPU computing, deep learning has been widely used in image denoising. This paper proposes a new denoising network model (RA-UNet) based on noise image pairs, which outperforms traditional methods in denoising performance and image quality.
Article
Engineering, Biomedical
Jingdong Yang, Jintu Zhu, Hailing Wang, Xin Yang
Summary: This study proposed a Dilated MultiResUNet network to improve end-to-end image segmentation performance based on U-Net, Res2Net, MultiResUNet, Dilated Residual Networks, and Squeeze-and-Excitation Networks. Evaluation on four biomedical datasets showed superior accuracy and generalization performance with significantly fewer parameters compared to the U-Net model.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Chemistry, Analytical
Haowu Tao, Wenhua Guo, Rui Han, Qi Yang, Jiyuan Zhao
Summary: In this study, a new image-denoising model is proposed, which utilizes convolutional neural networks to extract local features, attention similarity module (ASM) to focus on global information, and dilation convolution to enlarge receptive field. The model achieves better image-denoising effects, especially for complex blind noise and real images, as demonstrated by extensive experiments.
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.