ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Enhancing the Data Regularization Effect with Randomly Combined Features for Object Detection
Cited 1 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
Authors
Jiyeon Kim, Yong-Ju Lee, Yong-Hyuk Moon
Issue Date
2021-10
Citation
International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1065-1068
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICTC52510.2021.9620763
Project Code
21HS7200, Development of Adaptive and Lightweight Edge-Collaborative Analysis Technology for Enabling Proactive and Immediate Response and Rapid Learning, Moon Yong Hyuk
Abstract
Deep convolutional neural networks (CNNs) have made significant performance improvements on object detection and several augmentation techniques have been introduced to further improve the detection performance. We investigate how applying multiple augmentation techniques simultaneously can affect the learning capability of existing techniques and how providing more abundant training backgrounds to an image can have an effect. Our experimental results demonstrate that the performance has improved by combining Random Perceptive and Random Erasing techniques to Mosaic techniques on PASCAL VOC dataset. Our results also show that the combination of the augmentation techniques is also effective in small-sized specific datasets.
KSP Keywords
Augmentation techniques, Combined features, Convolution neural network(CNN), Deep convolutional neural networks, Learning Capability, Object detection, PASCAL VOC dataset, Small-sized, detection performance