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 | 75 | 9.83% |
Image Segmentation | 51 | 6.68% |
Medical Image Segmentation | 34 | 4.46% |
Denoising | 29 | 3.80% |
Self-Supervised Learning | 28 | 3.67% |
Image Classification | 28 | 3.67% |
Object Detection | 21 | 2.75% |
Classification | 21 | 2.75% |
Tumor Segmentation | 10 | 1.31% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |