Semantic Segmentation Models

Fully Convolutional Network

Introduced by Shelhamer et al. in Fully Convolutional Networks for Semantic Segmentation

Fully Convolutional Networks, or FCNs, are an architecture used mainly for semantic segmentation. They employ solely locally connected layers, such as convolution, pooling and upsampling. Avoiding the use of dense layers means less parameters (making the networks faster to train). It also means an FCN can work for variable image sizes given all connections are local.

The network consists of a downsampling path, used to extract and interpret the context, and an upsampling path, which allows for localization.

FCNs also employ skip connections to recover the fine-grained spatial information lost in the downsampling path.

Papers

Paper Code Results Date Stars