Spatial Pyramid Pooling (SPP) is a pooling layer that removes the fixed-size constraint of the network, i.e. a CNN does not require a fixed-size input image. Specifically, we add an SPP layer on top of the last convolutional layer. The SPP layer pools the features and generates fixed-length outputs, which are then fed into the fully-connected layers (or other classifiers). In other words, we perform some information aggregation at a deeper stage of the network hierarchy (between convolutional layers and fully-connected layers) to avoid the need for cropping or warping at the beginning.
Source: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 88 | 15.30% |
Object Detection | 77 | 13.39% |
Image Segmentation | 30 | 5.22% |
Decoder | 24 | 4.17% |
Image Classification | 18 | 3.13% |
Instance Segmentation | 13 | 2.26% |
Medical Image Segmentation | 12 | 2.09% |
Autonomous Driving | 12 | 2.09% |
Real-Time Object Detection | 11 | 1.91% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |