Cited 0 time in webofscience Cited 0 time in scopus

대용량 이미지넷 인식을 위한 CNN 기반 Weighted 앙상블 기법

Title
대용량 이미지넷 인식을 위한 CNN 기반 Weighted 앙상블 기법
Translated Title
CNN-based Weighted Ensemble Technique for ImageNet Classification
Authors
정희철최민국김준광권순정우영
DGIST Authors
최민국; 김준광; 권순정우영
Issue Date
2020-08
Citation
대한임베디드공학회논문지, 15(4), 197-204
Type
Article
Author Keywords
Deep learningImageNetILSVRCData augmentationEnsembleWeighted ensembleImage classification
ISSN
1975-5066
Abstract
The ImageNet dataset is a large scale dataset and contains various natural scene images. In this paper, we propose a convolutional neural network (CNN)-based weighted ensemble technique for the ImageNet classification task. First, in order to fuse several models, our technique uses weights for each model, unlike the existing average-based ensemble technique. Then we propose an algorithm that automatically finds the coefficients used in later ensemble process. Our algorithm sequentially selects the model with the best performance of the validation set, and then obtains a weight that improves performance when combined with existing selected models. We applied the proposed algorithm to a total of 13 heterogeneous models, and as a result, 5 models were selected. These selected models were combined with weights, and we achieved 3.297% Top-5 error rate on the ImageNet test dataset.
URI
http://hdl.handle.net/20.500.11750/12761
DOI
10.14372/IEMEK.2020.15.4.197
Publisher
대한임베디드공학회
Related Researcher
  • Author Jung, Wooyoung  
  • Research Interests Artificial Intelligence, Machine Learning, Autonomous Driving
Files:
There are no files associated with this item.
Collection:
Convergence Research Center for Future Automotive Technology1. Journal Articles
Division of Automotive Technology1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE