池化

From Ufldl

Jump to: navigation, search
Line 20: Line 20:
-----------------------------------------------------------------------------
-----------------------------------------------------------------------------
 +
To address this, first recall that we decided to obtain convolved features because images have the "stationarity" property, which implies that features that are useful in one region are also likely to be useful for other regions. Thus, to describe a large image, one natural approach is to aggregate statistics of these features at various locations. For example, one could compute the mean (or max) value of a particular feature over a region of the image. These summary statistics are much lower in dimension (compared to using all of the extracted features) and can also improve results (less over-fitting). We aggregation operation is called this operation pooling, or sometimes mean pooling or max pooling (depending on the pooling operation applied).  
To address this, first recall that we decided to obtain convolved features because images have the "stationarity" property, which implies that features that are useful in one region are also likely to be useful for other regions. Thus, to describe a large image, one natural approach is to aggregate statistics of these features at various locations. For example, one could compute the mean (or max) value of a particular feature over a region of the image. These summary statistics are much lower in dimension (compared to using all of the extracted features) and can also improve results (less over-fitting). We aggregation operation is called this operation pooling, or sometimes mean pooling or max pooling (depending on the pooling operation applied).  
Line 69: Line 70:
-----------------------------------------------------------------------------
-----------------------------------------------------------------------------
 +
== Formal description ==
== Formal description ==

Revision as of 11:45, 7 March 2013

Personal tools