Max pooling is directly followed by upsampling

[jackaceuser]

The network's structure contains max pooling immediately followed by upsampling.
Maybe I'm missing something but it doesn't seem to make any sense. And just removing it should improved results.

local pool7 = nn.SpatialMaxPooling(2,2,2,2)(conv7_relu)
local unpool00 = nn.SpatialUpSamplingNearest(2)(pool7)

Is there something specific that this structure addresses?

[zouchuhang]

@jackaceuser For perspective images with type prediction, the pooling operation is needed for shrinking down the parameters. But I agree with you for general case in solving panoramic/perspective images the max pooling + unsampling is a bit redundant. :)