0% Complete
Home
/
14th International Conference on Computer and Knowledge Engineering
Multi-source Ensemble Model for Scene Recognition
Authors :
Amir Hossein Saleknia
1
Ahmad Ayatollahi
2
1- School of Electrical Engineering, Iran University of Science and Technology
2- School of Electrical Engineering, Iran University of Science and Technology
Keywords :
Scene Recognition،Ensemble Learning،Test Time Augmentation
Abstract :
In computer vision, scene recognition is one of the most challenging research areas. A possible explanation may be the ambiguity between the various scene classes. Therefore, generating the highly discriminating features necessary for decent performance is a challenging task for a single Deep Neural Network (DNN). In this paper we propose a novel ensemble model for scene recognition. It is composed of multiple DNNs pre-trained for different tasks, each with its own strengths and capabilities. These models complement each other, so using them together can help us achieve higher accuracy than if we used just one alone. In addition, we propose Hard Sample Review (HSR), which is a form of adaptive Test Time Augmentation (TTA) with a lower computation cost and better performance. On the MIT-67 dataset, we achieved 90.15% accuracy by employing these techniques, indicating that the proposed method is superior to previous studies.
Papers List
List of archived papers
FGM Copula based Analysis of Coverage Region for Wireless Three-User Multiple Access Channel with Correlated Channel Coefficients
Mona Sadat Mohsenzadeh - Ghosheh Abed Hodtani
Financial Market Prediction Using Deep Neural Networks with Hardware Acceleration
Dara Rahmati - Mohammad Hadi Foroughi - Ali Bagherzadeh - Mehdi Foroughi - Saeid Gorgin
TriMAE: Fashion visual search with Triplet Masked Auto Encoder Vision Transformer
Lachin Zamani - Reza Azmi
Improving Machine Learning Classification of Heart Disease Using the Graph-Based Techniques
Abolfazl Dibaji - Sadegh Sulaimany
Compressing Deep Neural Networks Using Explainable AI
Kimia Soroush - Mohsen Raji - Behnam Ghavami
Robustness Scan of Digital Circuits Using Convolutional Neural Networks
Mobin Vaziri - Mohammad Mehdi Rahimifar - Hadi Jahanirad
FAST: FPGA Acceleration of Neural Networks Training
Alireza Borhani - Mohammad Hossein Goharinejad - Hamid Reza Zarandi
An influence maximization algorithm based on community detection using topological features
Zahra Aghaee - Afsaneh Fatemi
Intelligent Interpretation of Frequency Response Signatures to Diagnose Radial Deformation in Transformer Windings Using Artificial Neural Network
Reza Behkam - Hossein Karami - Mehdi Salay Naderi - Gevork B. Gharehpetian
A Novel Method For Fake News Detection Based on Propagation Tree
Mansour Davoudi - Mohammad Reza Moosavi - Mohammad Hadi Sadreddini
more
Samin Hamayesh - Version 41.3.1