Max Pooling is a pooling operation that calculates the maximum 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.
Image Source: here
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 65 | 7.49% |
Image Segmentation | 41 | 4.72% |
Denoising | 33 | 3.80% |
Medical Image Segmentation | 25 | 2.88% |
Image Classification | 24 | 2.76% |
Image Generation | 23 | 2.65% |
Computational Efficiency | 22 | 2.53% |
Deep Learning | 17 | 1.96% |
Object Detection | 16 | 1.84% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |