0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition
Authors :
Hamid Ahmadabadi
1
Omid Nejati Manzari
2
Ahmad Ayatollahi
3
1- School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
2- School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
3- School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
Keywords :
Action Recognition،Still Image،Deep Learning،Knowledge Distillation
Abstract :
This paper presents a study on improving human action recognition through the utilization of knowledge distillation, and the combination of CNN and ViT models. The research aims to enhance the performance and efficiency of smaller student models by transferring knowledge from larger teacher models. The proposed method employs a Transformer vision network as the student model, while a convolutional network serves as the teacher model. The teacher model extracts local image features, whereas the student model focuses on global features using an attention mechanism. The Vision Transformer (ViT) architecture is introduced as a robust framework for capturing global dependencies in images. Additionally, advanced variants of ViT, namely PVT, Convit, MVIT, Swin Transformer, and Twins, are discussed, highlighting their contributions to computer vision tasks. The ConvNeXt model is introduced as a teacher model, known for its efficiency and effectiveness in computer vision. The paper presents performance results for human action recognition on the Stanford 40 dataset, comparing the accuracy and mAP of student models trained with and without knowledge distillation. The findings illustrate that the suggested approach significantly improves the accuracy and mAP when compared to training networks under regular settings. These findings emphasize the potential of combining local and global features in action recognition tasks.
Papers List
List of archived papers
TrackMine: Topic Tracking in Model Mining using Genetic Algorithm
Mohammad Sajad Kasaei - Mohammadreza Sharbaf - Afsaneh Fatemi - Bahman Zamani
Classification of COVID-19 and Nodule in CT Images using Deep Convolutional Neural Network
Amirhossein Ghaemi - Seyyed Amir Mousavi mobarakeh - Habibollah Danyali - Kamran Kazemi
Deep Learning-Driven Beamforming Optimization for High-Performance 5G Planar Antenna Arrays
Rahman Mohammadi - Seyed Reza Razavi Pour
Impossible differential and zero-correlatin linear cryptanalysis of Marx, Marx2, Chaskey andSpeck32
Mahshid Saberi - Nasour Bagheri - Sadegh Sadeghi
Driving Violation Detection Using Vehicle Data and Environmental Conditions
Masood Ghasemi - Mahmood Fathy - Mohammad Shahverdy
A New Application of Machine Learning Based Methods for Disk Space Variation Fault Diagnosis in Transformer Windings
Reza Behkam - Amir Lotfi - Gevork B. Gharehpetian
Hybrid Vision Transformer for Detection of Dentigerous Cysts in Dental Radiography Images
Reza Tavasoli - Arya VarastehNezhad - Hamed Farbeh
Attention-Boosted Ensemble of Pre-trained Convolutional Neural Networks for Accurate Diabetic Retinopathy Detection
Benyamin Mirab Golkhatmi - Mohammad Hossein Moattar
Vaccine Distribution Modelling in Pandemics through Multi-Agent Systems: COVID-19 Case
Hossein Yarahmadi - Mohammad Ebrahim Shiri - Hamid Reza Navidi - Arash Sharifi - Moharram Challenger - Hassan Piriaei
Speech Emotion Recognition Using a Hierarchical Adaptive Weighted Multi-Layer Sparse Auto-Encoder Extreme Learning Machine with New Weighting and Spectral/SpectroTemporal Gabor Filter Bank Features
Fatemeh Daneshfar - Seyed Jahanshah Kabudian
more
Samin Hamayesh - Version 41.7.6