Filters








1,137 Hits in 5.8 sec

CuisineNet: Food Attributes Classification using Multi-scale Convolution Network [article]

Md. Mostafa Kamal Sarker, Mohammed Jabreel, Hatem A. Rashwan, Syeda Furruka Banu, Antonio Moreno, Petia Radeva, Domenec Puig
2018 arXiv   pre-print
The aggregation of multi-scale convolution layers with different kernel size is also used for weighting the features results from different scales.  ...  In addition, a joint loss function based on Negative Log Likelihood (NLL) is used to fit the model probability to multi labeled classes for multi-modal classification task.  ...  The authors gratefully acknowledge the support of NVIDIA Corporation with the donation of boards Titan Xp GPU.  ... 
arXiv:1805.12081v2 fatcat:lekncxubircoxlsmj2vxup2ifi

Identifying Dike-Pond System Using an Improved Cascade R-CNN Model and High-Resolution Satellite Images

Yintao Ma, Zheng Zhou, Xiaoxiong She, Longyu Zhou, Tao Ren, Shishi Liu, Jianwei Lu
2022 Remote Sensing  
This study improved the deep learning algorithm Cascade Region Convolutional Neural Network (Cascade R-CNN) algorithm to detect the DPS in Qianjiang City using high-resolution satellite data.  ...  In the proposed mCascade R-CNN, the regular convolution layer in the backbone was modified into the deformable convolutional layer, which was more suitable for learning the features of DPS with variable  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs14030717 fatcat:t2tmigdirre6tlldefhh6y3fpa

Fine-grained classification of grape leaves via a pyramid residual convolution neural network

Hanghao Li, 1. College of Information Engineering, Northwest A&F University, Yangling 712100, Shaanxi, China, Yana Wei, Hongming Zhang, Huan Chen, Jiangfei Meng, 2. College of Enology, Northwest A&F University, Yangling 712100, Shaanxi, China
2022 International Journal of Agricultural and Biological Engineering  
In this work, a pyramid residual convolution neural network was developed to classify images of eleven grape cultivars.  ...  The model extracts multi-scale feature maps of the leaf images through the convolution layer and enters them into three residual convolution neural networks.  ...  The proposed model and the commonly used convolution neural network classification models were evaluated using a dataset of leaves of 11 grape cultivars.  ... 
doi:10.25165/j.ijabe.20221502.6894 fatcat:x7iogtnavvfajaealohjvilmqi

Spatial-Aware Non-Local Attention for Fashion Landmark Detection [article]

Yixin Li, Shengqin Tang, Yun Ye, Jinwen Ma
2019 arXiv   pre-print
In order to tackle these problems, we propose Spatial-Aware Non-Local (SANL) block, an attentive module in deep neural network which can utilize spatial information while capturing global dependency.  ...  We then establish our fashion landmark detection framework on feature pyramid network, equipped with four SANL blocks in the backbone.  ...  neural networks.  ... 
arXiv:1903.04104v1 fatcat:5ckrmn5ufzball7kzfvi3mm2hy

A Sawn Timber Tree Species Recognition Method Based on AM-SPPResNet

Fenglong Ding, Ying Liu, Zilong Zhuang, Zhengguang Wang
2021 Sensors  
The spatial pyramid pooling and attention mechanism were used to improve the convolution layer of ResNet101 to extract the feature vector of sawn timber images.  ...  In this study, an optimized convolution neural network was proposed to process sawn timber image data to identify the tree species of the sawn timber.  ...  We all know that the classification layer of convolutional neural network is composed of multi-layer linear discriminator, which is similar to artificial neural network.  ... 
doi:10.3390/s21113699 pmid:34073445 fatcat:aolebira5bfslppztocwyk55ca

Extraction of Agricultural Fields via DASFNet with Dual Attention Mechanism and Multi-scale Feature Fusion in South Xinjiang, China

Rui Lu, Nan Wang, Yanbin Zhang, Yeneng Lin, Wenqiang Wu, Zhou Shi
2022 Remote Sensing  
Compared with different segmentation convolutional neural networks, DASFNet achieved the best testing accuracy in extracting fields with an F1-score of 0.9017, an intersection over a union of 0.8932, a  ...  This paper proposed a deep neural network with a dual attention mechanism and a multi-scale feature fusion (Dual Attention and Scale Fusion Network, DASFNet) to extract the cropland from a GaoFen-2 (GF  ...  Convolutional neural networks (CNN) are increasingly utilized in image analysis.  ... 
doi:10.3390/rs14092253 fatcat:z2aqg34ztfhmljh6ejytqbxini

Global Context Aware RCNN for Object Detection [article]

Wenchao Zhang, Chong Fu, Haoyu Xie, Mai Zhu, Ming Tie, Junxin Chen
2020 arXiv   pre-print
To tackle this problem, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between  ...  The core component of our GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively.  ...  of the neural network.  ... 
arXiv:2012.02637v1 fatcat:4njwl5ard5eund67zjgdwa6vmm

An Efficient Convolutional Neural Network for Remote-Sensing Scene Image Classification

Muhammad Ashad Baloch
2020 Journal of Computers  
Deep neural networks are providing a powerful solution for remote-sensing scene image classification.  ...  This research proposes a five-layer architecture which has fewer parameters compared with above state-of-the-art networks, and can be also complementary to other convolutional neural network features.  ...  Sajid Ali, Faculty, Department of Computer science Education University Lahore for his cooperation and supervision for acquiring this task and also providing the lab facilities for conducting the experimental  ... 
doi:10.17706/jcp.15.2.48-58 fatcat:uxnzqgpbtjgs3ksdou6kraftka

GourmetNet: Food Segmentation Using Multi-Scale Waterfall Features with Spatial and Channel Attention

Udit Sharma, Bruno Artacho, Andreas Savakis
2021 Sensors  
We propose GourmetNet, a single-pass, end-to-end trainable network for food segmentation that achieves state-of-the-art performance.  ...  Our novel architecture incorporates both channel attention and spatial attention information in an expanded multi-scale feature representation using our advanced Waterfall Atrous Spatial Pooling module  ...  DeepLab [5] is a popular architecture that proposed the Atrous Spatial Pyramid Pooling (ASPP) module, leveraging the use of atrous (dilated) convolutions [35] and Spatial Pyramid Pooling (SPP) [36  ... 
doi:10.3390/s21227504 pmid:34833577 pmcid:PMC8624046 fatcat:bs76l3pl2ngudkacvm5axxhkgi

ICICoS 2020 TOC

2020 2020 4th International Conference on Informatics and Computational Sciences (ICICoS)  
Waste Image Segmentation Using Convolutional Neural Network Encoder-Decoder with SegNet Architecture 15.45 - 16.00 1570677290 Tiani Tiara Putri, Ema Rachmawati, Febryanti Sthevanie Indonesian  ...  Balinese Carving Recognition using Pre-Trained Convolutional Neural Network 15.15 - 15.30 1570676888 Ni Putu Sutramiani, Nanik Suciati, Daniel Siahaan Transfer Learning on Balinese Character  ... 
doi:10.1109/icicos51170.2020.9299097 fatcat:nolsvoropvbjhal2stcfb77zui

Deep Convolutional Neural Networks for Weeds and Crops Discrimination From UAS Imagery

Leila Hashemi-Beni, Asmamaw Gebrehiwot, Ali Karimoddini, Abolghasem Shahbazi, Freda Dorbu
2022 Frontiers in Remote Sensing  
The classification accuracy achieved by U-Net is 77.9% higher than 62.6% of SegNet, 68.4% of FCN-32s, 77.2% of FCN-16s, and slightly lower than 81.1% of FCN-8s, and 84.3% of DepLab v3+.  ...  Herbicides are widely used in agriculture to control weeds; however, excessive use of herbicides in agriculture can lead to environmental pollution as well as yield reduction.  ...  The spatial pyramid pooling module is useful for encoding multiscale object information through multiple atrous convolutions with different rates.  ... 
doi:10.3389/frsen.2022.755939 fatcat:5rd2eu4hljgithp7frg2k3unla

A Deep-Learning-Based Approach for Wheat Yellow Rust Disease Recognition from Unmanned Aerial Vehicle Images

Qian Pan, Maofang Gao, Pingbo Wu, Jingwen Yan, Shilei Li
2021 Sensors  
the spatial generalization of the model.  ...  In addition, it was proposed to use the high-accuracy classification results of traditional algorithms as weak samples for wheat yellow rust identification.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21196540 pmid:34640873 pmcid:PMC8513082 fatcat:jmqop3j6yvc75eu7obkzoxyb4y

A Hierarchical deep model for food classification from photographs

2020 KSII Transactions on Internet and Information Systems  
Recent progress of deep learning techniques accelerates the recognition of food in a great scale.  ...  We build a hierarchical structure composed of deep CNN to recognize and classify food from photographs.  ...  They decomposed a video into spatial and temporal shots, and a sequence of shots are processed using a spatial temporal pyramid pooling (STPP) convNet with a long short-term memory or CNN-E model.  ... 
doi:10.3837/tiis.2020.04.016 fatcat:5lyy6nflmncohocwabghesfxxm

An Efficient Insect Pest Classification Using Multiple Convolutional Neural Network Based Models [article]

Hieu T. Ung, Huy Q. Ung, Binh T. Nguyen
2021 arXiv   pre-print
We present different convolutional neural network-based models in this work, including attention, feature pyramid, and fine-grained models.  ...  The experimental results show that combining these convolutional neural network-based models can better perform than the state-of-the-art methods on these two datasets.  ...  [24] investigated an insect pest classification problem using deep convolutional neural networks based on crop pest images.  ... 
arXiv:2107.12189v1 fatcat:y2iwhjktnrfzpckqb5bmxzzgva

Food Tray Sealing Fault Detection in Multi-Spectral Images Using Data Fusion and Deep Learning Techniques

Mohamed Benouis, Leandro D. Medus, Mohamed Saban, Abdessattar Ghemougui, Alfredo Rosado-Muñoz
2021 Journal of Imaging  
In the studied dataset, an accuracy of 88.7%, 88.3%, 89.3%, and 90.1% was achieved for Deep Belief Network (DBN), Extreme Learning Machine (ELM), Stacked Auto Encoder (SAE), and Convolutional Neural Network  ...  Recent advances in the field of food inspection have been related to the use of hyperspectral imaging technology and automated vision-based inspection systems.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/jimaging7090186 pmid:34564112 fatcat:2m6ji47aq5dipc7uyl6yvjbfia
« Previous Showing results 1 — 15 out of 1,137 results