A look inside the black box: Using graph-theoretical descriptors to interpret a Continuous-Filter Convolutional Neural Network (CF-CNN) trained on the global and local minimum energy structures of neutral water clusters

2020 ◽  
Vol 153 (2) ◽  
pp. 024302
Author(s):  
Jenna A. Bilbrey ◽  
Joseph P. Heindel ◽  
Malachi Schram ◽  
Pradipta Bandyopadhyay ◽  
Sotiris S. Xantheas ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Local Minimum ◽  
Water Clusters ◽  
Minimum Energy ◽  
Black Box ◽  
Continuous Filter ◽  
Neutral Water ◽  
Global And Local

scholarly journals Global and Local Attention-Based Free-Form Image Inpainting

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3204
Author(s):  
S. M. Nadim Uddin ◽  
Yong Ju Jung
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Image Inpainting ◽  
Experimental Results ◽  
Free Form ◽  
Local Similarity ◽  
Global And Local ◽  
Similarity Information

Deep-learning-based image inpainting methods have shown significant promise in both rectangular and irregular holes. However, the inpainting of irregular holes presents numerous challenges owing to uncertainties in their shapes and locations. When depending solely on convolutional neural network (CNN) or adversarial supervision, plausible inpainting results cannot be guaranteed because irregular holes need attention-based guidance for retrieving information for content generation. In this paper, we propose two new attention mechanisms, namely a mask pruning-based global attention module and a global and local attention module to obtain global dependency information and the local similarity information among the features for refined results. The proposed method is evaluated using state-of-the-art methods, and the experimental results show that our method outperforms the existing methods in both quantitative and qualitative measures.

scholarly journals Three-Dimensional Image Quality Evaluation and Optimization Based on Convolutional Neural Network

2021 ◽  
Vol 38 (4) ◽  
pp. 1041-1049
Author(s):  
Xiujuan Luo
Keyword(s):  
Neural Network ◽  
Image Quality ◽  
Convolutional Neural Network ◽  
3D Imaging ◽  
Quality Evaluation ◽  
Three Dimensional ◽  
3D Image ◽  
3D Images ◽  
Image Quality Evaluation ◽  
Global And Local

Currently, three-dimensional (3D) imaging has been successfully applied in medical health, movie viewing, games, and military. To make 3D images more pleasant to the eyes, the accurate judgement of image quality becomes the key step in content preparation, compression, and transmission in 3D imaging. However, there is not yet a satisfactory evaluation method that objectively assesses the quality of 3D images. To solve the problem, this paper explores the evaluation and optimization of 3D image quality based on convolutional neural network (CNN). Specifically, a 3D image quality evaluation model was constructed, and a 3D image quality evaluation algorithm was proposed based on global and local features. Next, the authors expounded on the preprocessing steps of salient regions in images, depicted the fusion process between global and local quality evaluations, and provided the way to process 3D image samples and acquire contrast-distorted images. The proposed algorithm was proved effective through experiments.

scholarly journals Generative Adversarial Network for Global Image-Based Local Image to Improve Malware Classification Using Convolutional Neural Network

2020 ◽  
Vol 10 (21) ◽  
pp. 7585
Author(s):  
Sejun Jang ◽  
Shuyu Li ◽  
Yunsick Sung
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Personal Information ◽  
Malware Detection ◽  
Generative Adversarial Network ◽  
Malware Classification ◽  
Adversarial Network ◽  
Global And Local ◽  
Malware Detection And Classification ◽  
Local Image

Malware detection and classification methods are being actively developed to protect personal information from hackers. Global images of malware (in a program that includes personal information) can be utilized to detect or classify it. This method is efficient, given that small changes in the program can be detected while maintaining the overall structure of the program. However, if any obfuscation approach that encrypts malware code is implemented, it becomes difficult to extract features such as opcodes and application programming interface functions. Given that malware detection and classification are performed differently depending on whether malware is obfuscated or not, methods that can simultaneously detect and classify general and obfuscated malware are required. This paper proposes a method that uses a generative adversarial network (GAN) and global image-based local image to classify unobfuscated and obfuscated malware. Global and local images of unobfuscated malware are generated using pixel and local feature visualizers. The GAN is utilized to visualize local features and generate local images of obfuscated malware by learning global and local images of unobfuscated malware. The local image of unobfuscated malware is merged with the global image generated via the pixel visualizer. To merge the global and local images of unobfuscated and obfuscated malware, the pixels extracted from global and local images are stored in a two-dimensional array, and then merged images are generated. Finally, unobfuscated and obfuscated malware are classified using a convolutional neural network (CNN). The results of experiments conducted on the Microsoft Malware Classification Challenge (BIG 2015) dataset indicate that the proposed method has a malware classification accuracy of 99.65%, which is 2.18% higher than that of the malware classification approach based on only global images and local features.

scholarly journals Dance Action Recognition and Pose Estimation Based on Deep Convolutional Neural Network

2021 ◽  
Vol 38 (2) ◽  
pp. 529-538
Author(s):  
Fengling Zhu ◽  
Ruichao Zhu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Action Recognition ◽  
Pose Estimation ◽  
Sampling Strategy ◽  
Local Features ◽  
Deep Convolutional Neural Network ◽  
Action Execution ◽  
Full Effect ◽  
Global And Local

Sports action recognition helps athletes correct their action range and standardize their poses. But it is not an easy task to recognize sports actions, due to the individual difference in action execution. Besides, the difficulty of action recognition increases with the diversity of actions and the complexity of background. The previous studies have not fully considered temporal changes, and failed to determine the exact staring point of actions. To solve the problem, this paper proposes a new method to recognize dance actions and estimate poses based on deep convolutional neural network (DCNN). Firstly, the authors presented full-effect expression of global and local features of dance actions, and derived an optimal model based on DeepPose. Next, a dance pose evaluation model was established based on time sequence segmentation network, and the sparse time sampling strategy was introduced to realize efficient and effective learning of the frame sequence of the whole video. Experimental results confirm the superiority of the full-effect expression of global and local features, and the effectiveness of the proposed model. The research results provide a reference for the application of deep learning (DL) in other scenarios of action recognition and pose estimation.

CONVOLUTIONAL NEURAL NETWORK BASED ALGORITHM FOR CECUM ACHIEVEMENT CONFIRMATION

2020 ◽  
Author(s):  
S Kashin ◽  
D Zavyalov ◽  
A Rusakov ◽  
V Khryashchev ◽  
A Lebedev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network
Sign in / Sign up

Export Citation Format

Share Document