Generalized Mean Pooling (GeM) computes the generalized mean of each channel in a tensor. Formally:
$$ \textbf{e} = \left[\left(\frac{1}{\Omega}\sum_{u\in{\Omega}}x^{p}_{cu}\right)^{\frac{1}{p}}\right]_{c=1,\cdots,C} $$
where $p > 0$ is a parameter. Setting this exponent as $p > 1$ increases the contrast of the pooled feature map and focuses on the salient features of the image. GeM is a generalization of the average pooling commonly used in classification networks ($p = 1$) and of spatial maxpooling layer ($p = \infty$).
Source: MultiGrain
Image Source: Eva Mohedano
Paper  Code  Results  Date  Stars 

Task  Papers  Share 

Image Retrieval  2  40.00% 
Dimensionality Reduction  1  20.00% 
General Classification  1  20.00% 
Image Classification  1  20.00% 
Component  Type 


🤖 No Components Found  You can add them if they exist; e.g. Mask RCNN uses RoIAlign 