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 | 8.99% |
Image Segmentation | 41 | 5.19% |
Decoder | 36 | 4.56% |
Image Generation | 33 | 4.18% |
Denoising | 32 | 4.05% |
Image Classification | 27 | 3.42% |
Self-Supervised Learning | 22 | 2.78% |
Medical Image Segmentation | 20 | 2.53% |
Object Detection | 19 | 2.41% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |