Research and Implementation of Autonomous Learning Platform for Image Classification

The image classification task aims to automatically classify image content based on machine learning methods. This task is a basic task in the field of computer vision, which has broad application prospects and great research value. At present, in the case of large-scale corpus annotation, mainstream image classification algorithms based on deep learning have been able to obtain better classification results. In order to achieve the above goals, this paper has carried out the following work. This paper studies two mainstream pre-training models in the field of image classification: one is the CNN network based on residual learning; the other is the Vision Transformer model based on Transformer. And according to the performance comparison of each model in four data sets: MNIST, CIFAR-10, CIFAR-100 and ImageNet under different parameters, the optimal model is selected as the background training model of the system. The experimental results show that the Transformer-based model Vision Transformer has better performance and can be used as the back-end training model of the autonomous learning platform.

[1]  Y. Liu,et al.  Learning Appearance-Motion Normality for Video Anomaly Detection , 2022, 2022 IEEE International Conference on Multimedia and Expo (ICME).

[2]  Y. Liu,et al.  Abnormal Event Detection with Self-guiding Multi-instance Ranking Framework , 2022, 2022 International Joint Conference on Neural Networks (IJCNN).

[3]  Zhao Tiancheng,et al.  Infrared Image Segmentation Method of Current Transformer Based on DeepLabv3+ Network , 2022, 2022 IEEE 5th International Electrical and Energy Conference (CIEEC).

[4]  Y. Liu,et al.  Learning Task-Specific Representation for Video Anomaly Detection with Spatial-Temporal Attention , 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Yang Liu,et al.  Collaborative Normality Learning Framework for Weakly Supervised Video Anomaly Detection , 2022, IEEE Transactions on Circuits and Systems II: Express Briefs.

[6]  Y. Liu,et al.  Appearance-Motion United Auto-Encoder Framework for Video Anomaly Detection , 2022, IEEE Transactions on Circuits and Systems II: Express Briefs.

[7]  S. Supratid,et al.  Impacts of Layer Sizes in Deep Residual-Learning Convolutional Neural Network on Flower Image Classification with Different class sizes , 2022, 2022 International Electrical Engineering Congress (iEECON).

[8]  S. Supratid,et al.  Effects of Shortcut-Level Amount in Lightweight ResNet of ResNet on Object Recognition with Distinct Number of Categories , 2022, 2022 International Electrical Engineering Congress (iEECON).

[9]  Jongsun Park,et al.  Low Complexity Gradient Computation Techniques to Accelerate Deep Neural Network Training , 2021, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Y. Liu,et al.  Learning Attention Augmented Spatial-temporal Normality for Video Anomaly Detection , 2021, 2021 3rd International Symposium on Smart and Healthy Cities (ISHC).

[11]  Meet Dave,et al.  Melanoma Detection Using Convolutional Neural Networks and Group Normalization , 2021, 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI).

[12]  Yu Li,et al.  Image recognition based on deep residual shrinkage Network , 2021, 2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA).

[13]  Mirco Ravanelli,et al.  Attention Is All You Need In Speech Separation , 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  K. Roy,et al.  DeepFakes Detection in Videos using Feature Engineering Techniques in Deep Learning Convolution Neural Network Frameworks , 2020, 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[15]  Yuda Chen,et al.  Research on Image Recognition of Supermarket Commodity Based on Convolutional Neural Network , 2019, 2019 12th International Symposium on Computational Intelligence and Design (ISCID).

[16]  Amanpreet Singh Brar,et al.  Support Vector based Indoor Scene Classification Technique using Different Features , 2019, 2019 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA).

[17]  Zhenghong Xiao,et al.  Fuzzy Neural Networks (FNNs) Training Algorithm With Dropout via Its Equivalent Fully Connected Fuzzy Inference Systems (F-CONFIS) , 2018, 2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC).

[18]  Kanta Tachibana,et al.  Wind Prediction Performance of Complex Neural Network with ReLU Activation Function , 2018, 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).

[19]  I Md. Dendi Maysanjaya,et al.  Abnormal Heart Rhythm Detection Based on Spectrogram of Heart Sound using Convolutional Neural Network , 2018, 2018 6th International Conference on Cyber and IT Service Management (CITSM).

[20]  Hichem Sahbi,et al.  Superpixel Partitioning of Very High Resolution Satellite Images for Large-Scale Classification Perspectives with Deep Convolutional Neural Networks , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[21]  Ruifang Liu,et al.  Stacked denoising autoencoder and dropout together to prevent overfitting in deep neural network , 2015, 2015 8th International Congress on Image and Signal Processing (CISP).

[22]  Zhen Wan,et al.  Time-dependent reliability analysis of cable-stayed bridge based on Monte-Carlo stochastic FEM , 2011, 2011 Second International Conference on Mechanic Automation and Control Engineering.

[23]  Yunli Lee,et al.  Human detection using Histogram of oriented gradients and Human body ratio estimation , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[24]  Wei Tang,et al.  Fast Approximated SIFT Applied in Moving Objects Detection , 2008, 2008 Chinese Conference on Pattern Recognition.

[25]  Jar-Ferr Yang,et al.  Linear Discriminant Regression Classification for Face Recognition , 2013, IEEE Signal Processing Letters.

[26]  Roger Lee,et al.  Computer and Information Science 2010 [outstanding papers from the 9th ACIS/IEEE International Conference on Computer and Information Science, Kaminoyama, Japan, August 18-20, 2010] , 2010, Computer and Information Science.

[27]  Li Zhao,et al.  An Enhanced LBP Feature Based on Facial Expression Recognition , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.