Semantic Segmentation Review

Submitted: June 27, 2018 Last updated: June 27, 2018
  • File:
  • Size:
    4.45 MB

Detailed Description

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.

Product and Performance Information


Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804