Pooling Operations
Average Pooling
Average Pooling is a pooling operation that calculates the average value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually used after a convolutional layer. It adds a small amount of translation invariance - meaning translating the image by a small amount does not significantly affect the values of most pooled outputs. It extracts features more smoothly than Max Pooling, whereas max pooling extracts more pronounced features like edges.
Image Source: here
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 48 | 6.87% |
| Semantic Segmentation | 35 | 5.01% |
| Object Detection | 32 | 4.58% |
| Self-Supervised Learning | 21 | 3.00% |
| Classification | 19 | 2.72% |
| Object | 17 | 2.43% |
| Image Segmentation | 15 | 2.15% |
| Decoder | 12 | 1.72% |
| Decision Making | 11 | 1.57% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
