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
Area-Efficient VLSI Implementation of Bit-Serial Multiplier Using Polynomial Basis over GF(2m)
Saeideh Nabipour - Javad Javidan - Gholamreza Zare Fatin
XAI for Transparent Autonomous Vehicles: A New Approach to Understanding Decision-Making in Self-driving Cars
Maryam Sadat Hosseini Azad - Amir Abbas Hamidi Imani - Shahriar Baradaran Shokouhi
Distilled BERT Model In Natural Language Processing
Yazdan Zandiye Vakili - Avisa Fallah - Hedieh Sajedi
A Comprehensive Dataset of Real-scene Images for Text Detection and Recognition in Persian
Iman Souzanchi - Ramin Rahimi - Mohammad Ali Majidi Anvari - Atefeh Baniasadi - Ashkan Sadeghi - Mohammad Reza Mohammadi
Automatic Infrared-Based Volume and Mass Estimation System for Agricultural Products
Seyed Muhammad Hossein Mousavi - S. Muhammad Hassan Mosavi
Novel Insights in Deep Learning for Predicting Climate Phenomena
Mohammad Naisipour - Saghar Ganji - Iraj Saeedpanah - Behnam Mehrakizadeh - Ahmad Reza Labibzadeh
An Interactive Approach for Query-based Multi-Document Scientific Text Summarization
Mohammadsadra Nejati - Azadeh Mohebi - Abbas Ahmadi
Lossless Watermarking in Encrypted Triangular Mesh Models Based on Optimized Vertex Estimation and Error Histogram Shifting
Alireza Ghaemi - Habibollah Danyali - Kamran Kazemi - Zahra Qodrati - Amirhossein Ghaemi - Seyedeh Masoumeh Taji
An overview of Business Intelligence research in healthcare organizations using a topic modeling approach
Mohammad Mehraeen - Laya Mahmoudi - Mohammad Hossein Sharifi
Adaptive Channel Estimation for MIMO-OFDM Systems in Impulsive Noise Environments
Mojtaba Hajiabadi
more
Samin Hamayesh - Version 41.7.6