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
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 45 | 7.26% |
Image Classification | 45 | 7.26% |
Semantic Segmentation | 30 | 4.84% |
Classification | 29 | 4.68% |
Self-Supervised Learning | 23 | 3.71% |
Quantization | 16 | 2.58% |
Reinforcement Learning (RL) | 11 | 1.77% |
Image Segmentation | 10 | 1.61% |
Autonomous Driving | 8 | 1.29% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |