ENet

Introduced by Paszke et al. in ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

ENet is a semantic segmentation architecture which utilises a compact encoder-decoder architecture. Some design choices include:

Using the SegNet approach to downsampling y saving indices of elements chosen in max pooling layers, and using them to produce sparse upsampled maps in the decoder.
Early downsampling to optimize the early stages of the network and reduce the cost of processing large input frames. The first two blocks of ENet heavily reduce the input size, and use only a small set of feature maps.
Using PReLUs as an activation function
Using dilated convolutions
Using Spatial Dropout

Source: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

Read Paper See Code

Paper	Code	Results	Date	Stars

Task	Papers	Share
Semantic Segmentation	13	23.21%
Autonomous Driving	5	8.93%
Image Segmentation	2	3.57%
Quantization	2	3.57%
Autonomous Vehicles	2	3.57%
Real-Time Semantic Segmentation	2	3.57%
Deep Learning	2	3.57%
regression	2	3.57%
Medical Image Analysis	2	3.57%

This feature is experimental; we are continuously improving our matching algorithm.