【语义分割】ENet -- A Deep Neural Network Architecture for Real-Time Semantic Segmentation

Network architecture

ENet的intial下采样使用的是结构(a)，后续的下采样均使用结构(b)：

This concat technique speeds up inference time of the initial block 10 times.

ENet的通用单元结构如下：

第一个1x1降维，第二个1x1升维

ENet不使用BN

Design choices

1、Feature map resolution

2、Early downsampling

3、Decoder size: a large encoder and a small decoder.

The encoder should be able to work in a similar fashion to original classification architectures, i.e. to operate on smaller resolution data and provide for information processing and filtering.

Instead, the role of the the decoder, is to upsample the output of the encoder, only fine-tuning the details.

4、Factorizing filters and Dilated convolutions

Results