scholarly journals Small Network for Lightweight Task in Computer Vision: A Pruning Method Based on Feature Representation

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Yisu Ge ◽  
Shufang Lu ◽  
Fei Gao
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Feature Representation ◽  
Fine Tuning ◽  
Practical Application ◽  
Pruning Algorithm ◽  
Network Pruning ◽  
Pruning Strategy ◽  
Speed Up ◽  
Network Compression

Many current convolutional neural networks are hard to meet the practical application requirement because of the enormous network parameters. For accelerating the inference speed of networks, more and more attention has been paid to network compression. Network pruning is one of the most efficient and simplest ways to compress and speed up the networks. In this paper, a pruning algorithm for the lightweight task is proposed, and a pruning strategy based on feature representation is investigated. Different from other pruning approaches, the proposed strategy is guided by the practical task and eliminates the irrelevant filters in the network. After pruning, the network is compacted to a smaller size and is easy to recover accuracy with fine-tuning. The performance of the proposed pruning algorithm is validated on the acknowledged image datasets, and the experimental results prove that the proposed algorithm is more suitable to prune the irrelevant filters for the fine-tuning dataset.

scholarly journals RESEARCH IN-DEPTH TRAINING OF NEURAL NETWORKS

2020 ◽  
Vol 70 (2) ◽  
pp. 234-238
Author(s):  
K.S. Imanbaev ◽  
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Language Processing ◽  
Back Propagation ◽  
Fine Tuning ◽  
Current State ◽  
Large Numbers ◽  
History Of ◽  
Propagation Of Errors

Currently, deep learning of neural networks is one of the most popular methods for speech recognition, natural language processing, and computer vision. The article reviews the history of deep learning of neural networks and the current state in General. We consider algorithms for training neural networks used for deep training of neural networks, followed by fine-tuning using the method of back propagation of errors. Neural networks with large numbers of hidden layers, frequently occurring and disappearing gradients are very difficult to train. In this paper, we consider methods that successfully implement training of neural networks with large numbers of layers (more than one hundred) and vanishing gradients. A review of well-known libraries used for successful deep learning of neural networks is conducted.

scholarly journals Better Communication Tool for Specially Disabled

2019 ◽  
Vol 8 (4) ◽  
pp. 3008-3011
Keyword(s):  
Neural Networks ◽  
Sign Language ◽  
Convolutional Neural Networks ◽  
Time Lapse ◽  
Normal Person ◽  
Communication Tool ◽  
Deep Convolutional Neural Networks ◽  
Detection Model ◽  
Pruning Strategy ◽  
Speed Up

Sign language is widely used when a dumb communicates. However, non-sign-language people find it difficult in interpreting them. So, we had come up with a system that enables speech impaired to speak with an artificial voice in public communities using Artificial intelligence techniques. we propose a hybrid-weighted metric known as weighted pruning in deep convolutional neural networks. In this work, we report experiments of weighted pruning. we show that using a weighted pruning strategy we can achieve significant speed up in Faster RCNN object detection model by discarding 50% of filters. In this paper we show evidences to our claim by reporting mean Average Precision of weighted pruned CNN is slightly higher than existing pruning techniques. The former part of the paper focus on moulding convolutional neural networks in terms of their speed and scalability for deploying them on mobiles, embedded and further small gadgets. The latter part of the paper describes novel approaches in letting dumb speak as fast as normal person in public, without time lapse using natural language algorithms and recommendations.

scholarly journals Research and Application of Improved AGP Algorithm for Structural Optimization Based on Feedforward Neural Networks

2015 ◽  
Vol 2015 ◽  
pp. 1-6
Author(s):  
Ruliang Wang ◽  
Huanlong Sun ◽  
Benbo Zha ◽  
Lei Wang
Keyword(s):  
Neural Networks ◽  
Structural Optimization ◽  
Network Performance ◽  
Feedforward Neural Networks ◽  
Improved Method ◽  
Pruning Algorithm ◽  
Network Pruning ◽  
Internal Relation ◽  
Traffic Capacity ◽  
Simulation Results

The adaptive growing and pruning algorithm (AGP) has been improved, and the network pruning is based on the sigmoidal activation value of the node and all the weights of its outgoing connections. The nodes are pruned directly, but those nodes that have internal relation are not removed. The network growing is based on the idea of variance. We directly copy those nodes with high correlation. An improved AGP algorithm (IAGP) is proposed. And it improves the network performance and efficiency. The simulation results show that, compared with the AGP algorithm, the improved method (IAGP) can quickly and accurately predict traffic capacity.

The machine training in problems of satellite images’s processing

Metrologiya ◽  
2020 ◽  
pp. 15-37
Author(s):  
L. P. Bass ◽  
Yu. A. Plastinin ◽  
I. Yu. Skryabysheva
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Computer Vision ◽  
Satellite Images ◽  
Vision Systems ◽  
Earth Remote Sensing ◽  
Practical Applications ◽  
Convolution Neural Networks ◽  
Computer Vision Systems ◽  
Trained Neural Network

Use of the technical (computer) vision systems for Earth remote sensing is considered. An overview of software and hardware used in computer vision systems for processing satellite images is submitted. Algorithmic methods of the data processing with use of the trained neural network are described. Examples of the algorithmic processing of satellite images by means of artificial convolution neural networks are given. Ways of accuracy increase of satellite images recognition are defined. Practical applications of convolution neural networks onboard microsatellites for Earth remote sensing are presented.

Algorithms for segmentation and recognition of objects on medical images based on chiarlet transformation and neural networks

2020 ◽  
pp. 35-45
Author(s):  
Y.A. Hamad ◽  
K.V. Simonov ◽  
A.S. Kents
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Computer Vision ◽  
Edge Detection ◽  
Medical Images ◽  
Classification Algorithms ◽  
Visual Data ◽  
Recognition Of Objects

The paper considers general approaches to image processing, analysis of visual data and computer vision. The main methods for detecting features and edges associated with these approaches are presented. A brief description of modern edge detection and classification algorithms suitable for isolating and characterizing the type of pathology in the lungs in medical images is also given.

TLBO-FLN: Teaching-Learning Based Optimization of Functional Link Neural Networks for Stock Closing Price Prediction

2020 ◽  
Vol 10 (4) ◽  
pp. 522-532 ◽  
Author(s):  
Sarat Chandra Nayak ◽  
Subhranginee Das ◽  
Mohammad Dilsad Ansari
Keyword(s):  
Neural Networks ◽  
Computational Cost ◽  
Optimization Techniques ◽  
Fine Tuning ◽  
Functional Link ◽  
Price Prediction ◽  
Closing Price ◽  
Teaching Learning Based Optimization ◽  
Artificial Neural ◽  
Teaching Learning

Background and Objective: Stock closing price prediction is enormously complicated. Artificial Neural Networks (ANN) are excellent approximation algorithms applied to this area. Several nature-inspired evolutionary optimization techniques are proposed and used in the literature to search the optimum parameters of ANN based forecasting models. However, most of them need fine-tuning of several control parameters as well as algorithm specific parameters to achieve optimal performance. Improper tuning of such parameters either leads toward additional computational cost or local optima. Methods: Teaching Learning Based Optimization (TLBO) is a newly proposed algorithm which does not necessitate any parameters specific to it. The intrinsic capability of Functional Link Artificial Neural Network (FLANN) to recognize the multifaceted nonlinear relationship present in the historical stock data made it popular and got wide applications in the stock market prediction. This article presents a hybrid model termed as Teaching Learning Based Optimization of Functional Neural Networks (TLBO-FLN) by combining the advantages of both TLBO and FLANN. Results and Conclusion: The model is evaluated by predicting the short, medium, and long-term closing prices of four emerging stock markets. The performance of the TLBO-FLN model is measured through Mean Absolute Percentage of Error (MAPE), Average Relative Variance (ARV), and coefficient of determination (R2); compared with that of few other state-of-the-art models similarly trained and found superior.

scholarly journals Bipolar Morphological Neural Networks: Gate-Efficient Architecture for Computer Vision

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Elena E. Limonova ◽  
Daniil M. Alfonso ◽  
Dmitry P. Nikolaev ◽  
Vladimir V. Arlazarov
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Morphological Neural Networks

scholarly journals Identifying Habitat Elements from Bird Images Using Deep Convolutional Neural Networks

Animals ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 1263
Author(s):  
Zhaojun Wang ◽  
Jiangning Wang ◽  
Congtian Lin ◽  
Yan Han ◽  
Zhaosheng Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Digital Technology ◽  
Rapid Development ◽  
Image Data ◽  
Image Database ◽  
Test Accuracy ◽  
Practical Application ◽  
Accuracy Rate ◽  
Deep Convolutional Neural Networks

With the rapid development of digital technology, bird images have become an important part of ornithology research data. However, due to the rapid growth of bird image data, it has become a major challenge to effectively process such a large amount of data. In recent years, deep convolutional neural networks (DCNNs) have shown great potential and effectiveness in a variety of tasks regarding the automatic processing of bird images. However, no research has been conducted on the recognition of habitat elements in bird images, which is of great help when extracting habitat information from bird images. Here, we demonstrate the recognition of habitat elements using four DCNN models trained end-to-end directly based on images. To carry out this research, an image database called Habitat Elements of Bird Images (HEOBs-10) and composed of 10 categories of habitat elements was built, making future benchmarks and evaluations possible. Experiments showed that good results can be obtained by all the tested models. ResNet-152-based models yielded the best test accuracy rate (95.52%); the AlexNet-based model yielded the lowest test accuracy rate (89.48%). We conclude that DCNNs could be efficient and useful for automatically identifying habitat elements from bird images, and we believe that the practical application of this technology will be helpful for studying the relationships between birds and habitat elements.

scholarly journals Towards pixel-to-pixel deep nucleus detection in microscopy images

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Fuyong Xing ◽  
Yuanpu Xie ◽  
Xiaoshuang Shi ◽  
Pingjun Chen ◽  
Zizhao Zhang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Deep Neural Networks ◽  
Image Data ◽  
Fine Tuning ◽  
Cell Detection ◽  
Imaging Protocol ◽  
Microscopy Image ◽  
Microscopy Images ◽  
Target Data

Abstract Background Nucleus or cell detection is a fundamental task in microscopy image analysis and supports many other quantitative studies such as object counting, segmentation, tracking, etc. Deep neural networks are emerging as a powerful tool for biomedical image computing; in particular, convolutional neural networks have been widely applied to nucleus/cell detection in microscopy images. However, almost all models are tailored for specific datasets and their applicability to other microscopy image data remains unknown. Some existing studies casually learn and evaluate deep neural networks on multiple microscopy datasets, but there are still several critical, open questions to be addressed. Results We analyze the applicability of deep models specifically for nucleus detection across a wide variety of microscopy image data. More specifically, we present a fully convolutional network-based regression model and extensively evaluate it on large-scale digital pathology and microscopy image datasets, which consist of 23 organs (or cancer diseases) and come from multiple institutions. We demonstrate that for a specific target dataset, training with images from the same types of organs might be usually necessary for nucleus detection. Although the images can be visually similar due to the same staining technique and imaging protocol, deep models learned with images from different organs might not deliver desirable results and would require model fine-tuning to be on a par with those trained with target data. We also observe that training with a mixture of target and other/non-target data does not always mean a higher accuracy of nucleus detection, and it might require proper data manipulation during model training to achieve good performance. Conclusions We conduct a systematic case study on deep models for nucleus detection in a wide variety of microscopy images, aiming to address several important but previously understudied questions. We present and extensively evaluate an end-to-end, pixel-to-pixel fully convolutional regression network and report a few significant findings, some of which might have not been reported in previous studies. The model performance analysis and observations would be helpful to nucleus detection in microscopy images.

Sign in / Sign up

Export Citation Format

Share Document