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 | 71 | 9.03% |
Image Segmentation | 40 | 5.09% |
Decoder | 36 | 4.58% |
Denoising | 32 | 4.07% |
Image Generation | 32 | 4.07% |
Image Classification | 27 | 3.44% |
Self-Supervised Learning | 21 | 2.67% |
Medical Image Segmentation | 20 | 2.54% |
Object Detection | 19 | 2.42% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |