Pooling Operations

Strip Pooling

Introduced by Hou et al. in Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

Strip Pooling is a pooling strategy for scene parsing which considers a long but narrow kernel, i.e., $1\times{N}$ or $N\times{1}$. As an alternative to global pooling, strip pooling offers two advantages. First, it deploys a long kernel shape along one spatial dimension and hence enables capturing long-range relations of isolated regions. Second, it keeps a narrow kernel shape along the other spatial dimension, which facilitates capturing local context and prevents irrelevant regions from interfering the label prediction. Integrating such long but narrow pooling kernels enables the scene parsing networks to simultaneously aggregate both global and local context. This is essentially different from the traditional spatial pooling which collects context from a fixed square region.

Source: Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Decoder 1 9.09%
Deblurring 1 9.09%
Image Deblurring 1 9.09%
Image Restoration 1 9.09%
Blocking 1 9.09%
Image Compression 1 9.09%
MS-SSIM 1 9.09%
Depth Estimation 1 9.09%
Monocular Depth Estimation 1 9.09%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories