Paper U-Net: Convolutional Networks for Biomedical Image SegmentationThere is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotatedarxiv.orgAbstract딥러닝 학습에는 수천 개 이상의 annotation 학습 데이터가 필요하다.context 포착을 위한 ..

paper EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksConvolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing narxiv.orgAbstract기존 CNN은 한정된 자원에서 개발하고, 자원이 충분해지면 성능 개선을 위한 scal..