예술 작품 아티스트 분류의 정확도 향상을 위한 CNN 구조 최적화
Optimizing CNN Structure to Improve Accuracy of Artwork Artist Classification
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
컴퓨터 비전 분류 연구에서 합성곱 신경망 (Convolutional Neural Network)은 탁월한 이미지 분류성능을 보여준다. 이에 영감을 받아 예술 관련 이미지 분류 작업에 대한 적용 가능성을 분석해본다. 본 논문에서는 예술 작품 아티스트 분류의 정확도를 향상시키기 위해 최적화된 합성곱 신경망 구조를 제안한다. 미세 조정 범위 시나리오와 완전연결층 조정 시나리오를 세운 뒤 그에 따른 예술 작품 아티스트 분류의 정확도를 측정했다. 즉, 학습 컨볼루션 레이어(Convolution layer) 수와 완전연결층 수 등 ResNet50 모델의 구조를 변경하며 예술 작품 아티스트 분류의 정확도가 향상되도록 최적화했다. 본 논문에서 제안하는 합성곱 신경망 구조는 기존 예술 작품 아티스트 분류에서 쓰이던 AlexNet 모델을 1-GPU 버전으로 수정한 CaffeNet 모델보다 더 높은 정확도를 실험결과에서 증명한다.
Abstract
Metaverse is a modern new technology that is advancing quickly. The goal of this study is to investigate this technique from the perspective of computer vision as well as general perspective. A thorough analysis of computer vision related Metaverse topics has been done in this study. Its history, method, architecture, benefits, and drawbacks are all covered. The Metaverse's future and the steps that must be taken to adapt to this technology are described. The concepts of Mixed Reality (MR), Augmented Reality (AR), Extended Reality (XR) and Virtual Reality (VR) are briefly discussed. The role of computer vision and its application, advantages and disadvantages and the future research areas are discussed.
참고문헌 (16)
- Alex Krizhevsky, "ImageNet classification with deep convolutional neural networks", Communications of the ACM, 60(6), pp.84~90 (2017), Association for Computing Machinery (ACM)[DOI]
- Jia Deng, "ImageNet : A large-scale hierarchical image database", 2009IEEE Conference on Computer Vision and Pattern Recognition, pp.1063~6919 (2009)
- Angie K. Reyes, "Fine-tuning Deep Convolutional Networks for Plant Recognition", CEUR Workshop Proceedings, 1391 (2015)
- K. He, "Deep Residual Learning for Image Recognition", 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.770~778 (2016)
- Sergey Karayev, "Recognizing Image Style", British Machine Vision Conference, 3, pp.11~ (2014)
- Eva Cetinic, "Fine-tuning Convolutional Neural Networks for fine art classification", Expert Systems with Applications, 114, pp.107~118 (2018), Elsevier BV[DOI]
- Alex Krizhevsky, "ImageNet classification with deep convolutional neural networks", Communications of the ACM, 60(6), pp.84~90 (2017), Association for Computing Machinery (ACM)[DOI]
- Yuri Sousa Aurelio, "Learning from Imbalanced Data Sets with Weighted Cross-Entropy Function", Neural Processing Letters, 50(2), pp.1937~1949 (2019), Springer Science and Business Media LLC[DOI]
- Agnieszka Mikołajczyk, "Data augmentation for improving deep learning in image classification problem", International Interdisciplinary PhD Workshop (IIPhDW) (2018)
- Agung W. Setiawan, "Color retinal image enhancement using CLAHE", International Conference on ICT for Smart Society (2013)
- Sangdoo Yun, "CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features", the IEEE International Conference on Computer Vision, pp.6023~3032 (2019)
- Hongyi Zhang, "mixup : Beyond Empirical Risk Minimization", International Conference on Learning Representations, ICLR (2018)
- Terrance DeVries, "Improved Regularization of Convolutional Neural Networks with Cutout", The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1~8 (2017)
- SZEGEDY, Christian, "Going deeper with convolutions", The IEEE conference on computer vision and pattern recognition (2015)
- Yangqing Jia, "Caffe: Convolutional Architecture for Fast Feature Embedding", ACM Multimedia, pp.675~678 (2014)[DOI]