Pooling Operations
Generalized Mean Pooling
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 max-pooling layer ($p = \infty$).
Source: MultiGrain
Image Source: Eva Mohedano
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Retrieval | 3 | 16.67% |
| Retrieval | 3 | 16.67% |
| Physical Simulations | 1 | 5.56% |
| Decoder | 1 | 5.56% |
| Philosophy | 1 | 5.56% |
| Gait Recognition | 1 | 5.56% |
| Multiview Gait Recognition | 1 | 5.56% |
| Content-Based Image Retrieval | 1 | 5.56% |
| Deep Learning | 1 | 5.56% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
