2
$\begingroup$

In paper Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs, in Section 3.4, it said

Since, the aim of this work is to estimate high-resolution and high-quality density maps, F-CNN is constructed using a set of convolutional and fractionally-strided convolutional layers. The set of fractionally-strided convolutional layers help us to restore details in the output density maps. The following structure is used for F-CNN: CR(64,9)-CR(32,7)- TR(32)-CR(16,5)-TR(16)-C(1,1), where, C is convolutional layer, R is ReLU layer, T is fractionally-strided convolution layer and the first number inside every brace indicates the number of filters while the second number indicates filter size. Every fractionally-strided convolution layer increases the input resolution by a factor of 2, thereby ensuring that the output resolution is the same as that of input.

I would like to know the detail of fractionally-strided convolution layer.

$\endgroup$
2
$\begingroup$

Here is an animation of fractionally-strided convolution (from this github project):

where the dashed white cells are zero rows/columns padded between the input cells (blue). These animations are visualizations of the mathematical formulas from the article below:

A guide to convolution arithmetic for deep learning

Here is a quote from the article:

Figure [..] helps understand what fractional strides involve: zeros are inserted between input units, which makes the kernel move around at a slower pace than with unit strides [footnote: doing so is inefficient and real-world implementations avoid useless multiplications by zero, but conceptually it is how the transpose of a strided convolution can be thought of.]


Also, here is a post on this site asking "What are deconvolutional layers?" which is the same thing.

And here are two quotes from a post by Paul-Louis Pröve on different types of convolutions:

Transposed Convolutions (a.k.a. deconvolutions or fractionally strided convolutions)

and

Some sources use the name deconvolution, which is inappropriate because it’s not a deconvolution [..] An actual deconvolution reverts the process of a convolution.

|improve this answer|||||
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.