Deeplabv3+ 阅读笔记

Notes: 谷歌deeplabv3+的代码现在已经开源，详见deeplab(Github)，还有一个使用的demo样例。

0.

spatial pyramid pooling

• probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view
• encode multi-scale contextual information

encode-decoder

• gradually recovering the spatial information
• capture sharper object boundaries

convolution

• depthwise convolution: a spatial convolution performed independently over each channel of an input
• pointwise convolution: a 1x1 convolution, projecting the channels output by the depthwise convolution onto a new channel space
• differences:
  
  • Inception: 1x1 conv first
  • depthvise separable convolution: channel-wise first

details can be found here.

contributes

1. decoder module: refine the segmentation results especially along object boundaries
2. depth-wise separable convolution
   
   • Atrous Spatial Pyramid Pooling
   • decoder

3. Methods

• capture multi-scale context