Semantic Segmentation Review
- File: Semantic_segmentation_review_2018.05.25.pdf
- Size:4.25 MB
We provide an overview with a lot of references to the classical and recent papers on the semantic segmentation, such as Fully Convolution Networks, U-Net, DeepLab, PSPNet, etc. It covers the most common and well-performing approaches to building network architectures and benchmarking. Most popular datasets and evaluation metrics are also provided.
The target audience is Machine Learning enthusiasts and practitioners who are familiar with the basic concepts of Deep Learning and want to learn more about how to apply the same apparatus to the semantic segmentation problem.