Semantic Segmentation Models

DeepLab is a semantic segmentation architecture. First, the input image goes through the network with the use of dilated convolutions. Then the output from the network is bilinearly interpolated and goes through the fully connected CRF to fine tune the result we obtain the final predictions.

Source: Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Papers


Paper Code Results Date Stars

Tasks


Categories