论文标题:Image Segmentation Using Deep Learning:A Survey
作者:
发表日期:
阅读日期 :
研究背景:scene understanding,medical image analysis, robotic perception, video surveillance, augmented reality, and image compression
方法和性质: fully convolutional pixel-labeling networks,encoder-decoder architectures, multi-scale and pyramid based approaches, recurrent networks, visual attention models, and generativemodels in adversarial settings.
Fully convolutional networks
Convolutional models with graphical models
Encoder-decoder based models
Multi-scale and pyramid network based models5) R-CNN based models (for instance segmentation)6) Dilated convolutional models and DeepLab family7) Recurrent neural network based models8) Attention-based models