CNN 기술 개발 동향(U-Net, V-Net 중심)
U-Net과 V-Net은 medical image segmentation에 많이 사용한다.
U-Net : the segmentation of biological microscopy images
V-Net : data augmentation strategy to leverage from the available annotated image
- a contracting sub-net to encode the semantics and context information
- an expanding sub-net uses and decodes the encoded informa-tion for the generation of segmented maps.
VGG16 : 16층으로 구성된 CNN모듈
ImageNet : is a dataset of over 15 million labeled high-resolution images belonging to roughly 22,000 categories.
The images were collected from the web and labeled by human labelers
참조 :
1. 논문 : Medical Image Segmentation Using a U-Net type of Architecture arxiv.org/pdf/2005.05218.pdf
2. 강의 : youtu.be/yG6GbEtGUrU
3. 블로그 : bskyvision.com/504
4. VGG16 논문. 소스 : neurohive.io/en/popular-networks/vgg16/
인공지능 음성, 언어, 영상 분석/처리 전문기업 bory.io
제휴 협력 bory@bory.io