Fine-Grained Visual Computing Based on Deep Learning

2021 ◽  
Vol 17 (1s) ◽  
pp. 1-19
Author(s):  
Zhihan Lv ◽  
Liang Qiao ◽  
Amit Kumar Singh ◽  
Qingjun Wang
Keyword(s):  
Attention Mechanism ◽  
Image Feature ◽  
Classification Model ◽  
Strong Positive Correlation ◽  
Image Categorization ◽  
Training Time ◽  
Fine Grained ◽  
Visual Computing ◽  
Multi Level ◽  
Categorization Model

With increasing amounts of information, the image information received by people also increases exponentially. To perform fine-grained categorization and recognition of images and visual calculations, this study combines the Visual Geometry Group Network 16 model of convolutional neural networks and the vision attention mechanism to build a multi-level fine-grained image feature categorization model. Finally, the TensorFlow platform is utilized to simulate the fine-grained image classification model based on the visual attention mechanism. The results show that in terms of accuracy and required training time, the fine-grained image categorization effect of the multi-level feature categorization model constructed by this study is optimal, with an accuracy rate of 85.3% and a minimum training time of 108 s. In the similarity effect analysis, it is found that the chi-square distance between Log Gabor features and the degree of image distortion show a strong positive correlation; in addition, the validity of this measure is verified. Therefore, through the research in this study, it is found that the constructed fine-grained image categorization model has higher accuracy in image recognition categorization, shorter training time, and significantly better performance in similar feature effects, which provides an experimental reference for the visual computing of fine-grained images in the future.

scholarly journals Fine-Grained Image Classification for Crop Disease Based on Attention Mechanism

2020 ◽  
Vol 11 ◽  
Author(s):  
Guofeng Yang ◽  
Yong He ◽  
Yong Yang ◽  
Beibei Xu
Keyword(s):  
Image Classification ◽  
Classification Accuracy ◽  
Attention Mechanism ◽  
Classification Model ◽  
Classification Models ◽  
Fine Grained ◽  
Complex Scenes ◽  
Crop Disease ◽  
Visual Disturbances

Fine-grained image classification is a challenging task because of the difficulty in identifying discriminant features, it is not easy to find the subtle features that fully represent the object. In the fine-grained classification of crop disease, visual disturbances such as light, fog, overlap, and jitter are frequently encountered. To explore the influence of the features of crop leaf images on the classification results, a classification model should focus on the more discriminative regions of the image while improving the classification accuracy of the model in complex scenes. This paper proposes a novel attention mechanism that effectively utilizes the informative regions of an image, and describes the use of transfer learning to quickly construct several fine-grained image classification models of crop disease based on this attention mechanism. This study uses 58,200 crop leaf images as a dataset, including 14 different crops and 37 different categories of healthy/diseased crops. Among them, different diseases of the same crop have strong similarities. The NASNetLarge fine-grained classification model based on the proposed attention mechanism achieves the best classification effect, with an F1 score of up to 93.05%. The results show that the proposed attention mechanism effectively improves the fine-grained classification of crop disease images.

scholarly journals Improved SinGAN Integrated with an Attentional Mechanism for Remote Sensing Image Classification

2021 ◽  
Vol 13 (9) ◽  
pp. 1713
Author(s):  
Songwei Gu ◽  
Rui Zhang ◽  
Hongxia Luo ◽  
Mengyao Li ◽  
Huamei Feng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Real Life ◽  
Attention Mechanism ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Natural Image ◽  
Remote Sensing Images ◽  
Training Time ◽  
Adversarial Networks ◽  
Remote Sensing Image Classification

Deep learning is an important research method in the remote sensing field. However, samples of remote sensing images are relatively few in real life, and those with markers are scarce. Many neural networks represented by Generative Adversarial Networks (GANs) can learn from real samples to generate pseudosamples, rather than traditional methods that often require more time and man-power to obtain samples. However, the generated pseudosamples often have poor realism and cannot be reliably used as the basis for various analyses and applications in the field of remote sensing. To address the abovementioned problems, a pseudolabeled sample generation method is proposed in this work and applied to scene classification of remote sensing images. The improved unconditional generative model that can be learned from a single natural image (Improved SinGAN) with an attention mechanism can effectively generate enough pseudolabeled samples from a single remote sensing scene image sample. Pseudosamples generated by the improved SinGAN model have stronger realism and relatively less training time, and the extracted features are easily recognized in the classification network. The improved SinGAN can better identify sub-jects from images with complex ground scenes compared with the original network. This mechanism solves the problem of geographic errors of generated pseudosamples. This study incorporated the generated pseudosamples into training data for the classification experiment. The result showed that the SinGAN model with the integration of the attention mechanism can better guarantee feature extraction of the training data. Thus, the quality of the generated samples is improved and the classification accuracy and stability of the classification network are also enhanced.

scholarly journals Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models

2021 ◽  
pp. 109434202110109
Author(s):  
Sam Ade Jacobs ◽  
Tim Moon ◽  
Kevin McLoughlin ◽  
Derek Jones ◽  
David Hysom ◽  
...  
Keyword(s):  
Small Molecule ◽  
Molecular Design ◽  
Turnaround Time ◽  
Generative Models ◽  
Quality Model ◽  
Training Time ◽  
Small Molecule Drug ◽  
Training Approach ◽  
Previous State ◽  
Multi Level

We improved the quality and reduced the time to produce machine learned models for use in small molecule antiviral design. Our globally asynchronous multi-level parallel training approach strong scales to all of Sierra with up to 97.7% efficiency. We trained a novel, character-based Wasserstein autoencoder that produces a higher quality model trained on 1.613 billion compounds in 23 minutes while the previous state of the art takes a day on 1 million compounds. Reducing training time from a day to minutes shifts the model creation bottleneck from computer job turnaround time to human innovation time. Our implementation achieves 318 PFLOPs for 17.1% of half-precision peak. We will incorporate this model into our molecular design loop enabling the generation of more diverse compounds; searching for novel, candidate antiviral drugs improves and reduces the time to synthesize compounds to be tested in the lab.

scholarly journals From Barriers to Enablers: The Role of Organizational Learning in Transitioning SMEs into the Circular Economy

2021 ◽  
Vol 13 (3) ◽  
pp. 1021
Author(s):  
Sara Scipioni ◽  
Meir Russ ◽  
Federico Niccolini
Keyword(s):  
Organizational Learning ◽  
Circular Economy ◽  
Business Models ◽  
Small And Medium Enterprises ◽  
Sustainable Business ◽  
Fine Grained ◽  
Contextual Elements ◽  
Transfer And Retention ◽  
Multi Level ◽  
Medium Enterprises

To contribute to small and medium enterprises’ (SMEs) sustainable transition into the circular economy, the study proposes the activation of organizational learning (OL) processes—denoted here as multi-level knowledge creation, transfer, and retention processes—as a key phase in introducing circular business models (CBMs) at SME and supply chain (SC) level. The research employs a mixed-method approach, using the focus group methodology to identify contextual elements impacting on CBM-related OL processes, and a survey-based evaluation to single out the most frequently used OL processes inside Italian construction SMEs. As a main result, a CBM-oriented OL multi-level model offers a fine-grained understanding of contextual elements acting mutually as barriers and drivers for OL processes, as possible OL dynamics among them. The multi-level culture construct—composed of external stakeholders’, SC stakeholders’, and organizational culture—identify the key element to activate CBM-oriented OL processes. Main implications are related to the identification of cultural, structural, regulatory, and process contextual elements across the external, SC, and organizational levels, and their interrelation with applicable intraorganizational and interorganizational learning processes. The proposed model would contribute to an improved implementation of transitioning into the circular economy utilizing sustainable business models in the construction SMEs.

The influence of benthic diatoms on the textures of carbonate-coated grains from a fluvial tufa spring in northern California

2020 ◽  
Vol 90 (11) ◽  
pp. 1601-1613
Author(s):  
Hannah P. Boelts ◽  
Yadira Ibarra ◽  
Clive Hayzelden
Keyword(s):  
Pore Space ◽  
Strong Positive Correlation ◽  
Northern California ◽  
Threshold Size ◽  
Fine Grained ◽  
Henry Cowell ◽  
Marine Carbonate ◽  
Pore Area ◽  
Freshwater Spring ◽  
Imagej Software

ABSTRACT Diatoms are common in terrestrial freshwater carbonate environments, but their influence on the resulting carbonate texture and porosity remains unquantified. This study investigates the effect of diatoms on the textural variability and syndepositional porosity of spring-associated carbonate coated grains from a freshwater spring in Henry Cowell State Park, northern California, USA. Carbonate coated grains (n = 60) were collected from the distal-most pool of the spring (∼ 300 m from the spring source) and the porosity of the 1 cm diameter fraction (n = 20) was determined using the ImageJ software by adjusting the threshold size for pores > 1000 μm2. Results reveal a strong positive correlation between the number of pores and the number of diatoms examined in each coated grain (r = 0.77). There is a moderate positive relationship between the length of the largest diatom and the minor-axis diameter of a best-fit ellipse of its corresponding pore (r = 0.60). The total pore area for pores associated with at least one diatom was significantly greater than the total pore area of pores that did not enclose diatom frustules (t = 1.80, p < 0.05). Textural observations show that fine-grained laminated textures contain fewer diatoms than the porous textures, suggesting that diatoms disrupt lamination continuity by introducing pore space. These findings have implications for the influence of diatoms on the syndepositional porosity of carbonate rocks from the Cretaceous to Recent and may help explain textural differences between modern marine carbonate microbialites and their Precambrian counterparts.

scholarly journals Person Reidentification Model Based on Multiattention Modules and Multiscale Residuals

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yongyi Li ◽  
Shiqi Wang ◽  
Shuang Dong ◽  
Xueling Lv ◽  
Changzhi Lv ◽  
...  
Keyword(s):  
Local Features ◽  
Attention Mechanism ◽  
Experimental Results ◽  
Original Network ◽  
Fine Grained ◽  
Backbone Network ◽  
Model Based ◽  
Local Branch ◽  
Feature Expression ◽  
Global And Local

At present, person reidentification based on attention mechanism has attracted many scholars’ interests. Although attention module can improve the representation ability and reidentification accuracy of Re-ID model to a certain extent, it depends on the coupling of attention module and original network. In this paper, a person reidentification model that combines multiple attentions and multiscale residuals is proposed. The model introduces combined attention fusion module and multiscale residual fusion module in the backbone network ResNet 50 to enhance the feature flow between residual blocks and better fuse multiscale features. Furthermore, a global branch and a local branch are designed and applied to enhance the channel aggregation and position perception ability of the network by utilizing the dual ensemble attention module, as along as the fine-grained feature expression is obtained by using multiproportion block and reorganization. Thus, the global and local features are enhanced. The experimental results on Market-1501 dataset and DukeMTMC-reID dataset show that the indexes of the presented model, especially Rank-1 accuracy, reach 96.20% and 89.59%, respectively, which can be considered as a progress in Re-ID.

DeepEnzyPred: A Bi-Layered Deep Learning Framework for prediction of Bacteriophage Enzymes and their Sub-Hydrolases Enzymes via Novel Multi Level- Multi Thresholds Feature Selection technique

2020 ◽  
Author(s):  
Yu Wang ◽  
ZAHEER ULLAH KHAN ◽  
Shaukat Ali ◽  
Maqsood Hayat
Keyword(s):  
Feature Selection ◽  
Bacterial Infections ◽  
Large Scale ◽  
Computational Models ◽  
Genetic Material ◽  
Feature Space ◽  
Classification Model ◽  
Antibacterial Drug ◽  
Accurate Identification ◽  
Multi Level

Abstract BackgroundBacteriophage or phage is a type of virus that replicates itself inside bacteria. It consist of genetic material surrounded by a protein structure. Bacteriophage plays a vital role in the domain of phage therapy and genetic engineering. Phage and hydrolases enzyme proteins have a significant impact on the cure of pathogenic bacterial infections and disease treatment. Accurate identification of bacteriophage proteins is important in the host subcellular localization for further understanding of the interaction between phage, hydrolases, and in designing antibacterial drugs. Looking at the significance of Bacteriophage proteins, besides wet laboratory-based methods several computational models have been developed so far. However, the performance was not considerable due to inefficient feature schemes, redundancy, noise, and lack of an intelligent learning engine. Therefore we have developed an anovative bi-layered model name DeepEnzyPred. A Hybrid feature vector was obtained via a novel Multi-Level Multi-Threshold subset feature selection (MLMT-SFS) algorithm. A two-dimensional convolutional neural network was adopted as a baseline classifier.ResultsA conductive hybrid feature was obtained via a serial combination of CTD and KSAACGP features. The optimum feature was selected via a Novel Multi-Level Multi-Threshold Subset Feature selection algorithm. Over 5-fold jackknife cross-validation, an accuracy of 91.6 %, Sensitivity of 63.39%, Specificity 95.72%, MCC of 0.6049, and ROC value of 0.8772 over Layer-1 were recorded respectively. Similarly, the underline model obtained an Accuracy of 96.05%, Sensitivity of 96.22%, Specificity of 95.91%, MCC of 0.9219, and ROC value of 0.9899 over layer-2 respectivily.ConclusionThis paper presents a robust and effective classification model was developed for bacteriophage and their types. Primitive features were extracted via CTD and KSAACGP. A novel method (MLMT-SFS ) was devised for yielding optimum hybrid feature space out of primitive features. The result drew over hybrid feature space and 2D-CNN shown an excellent classification. Based on the recorded results, we believe that the developed predictor will be a valuable resource for large scale discrimination of unknown Phage and hydrolase enzymes in particular and new antibacterial drug design in pharmaceutical companies in general.

Sign in / Sign up

Export Citation Format

Share Document