A Global Convolutional Network, or GCN, is a semantic segmentation building block that utilizes a large kernel to help perform classification and localization tasks simultaneously. It can be used in a FCN-like structure, where the GCN is used to generate semantic score maps. Instead of directly using larger kernels or global convolution, the GCN module employs a combination of $1 \times k + k \times 1$ and $k \times 1 + 1 \times k$ convolutions, which enables dense connections within a large $k\times{k}$ region in the feature map
Source: Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional NetworkPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 4 | 33.33% |
Image Super-Resolution | 1 | 8.33% |
Pansharpening | 1 | 8.33% |
Super-Resolution | 1 | 8.33% |
Instance Segmentation | 1 | 8.33% |
Object Detection | 1 | 8.33% |
Open-Ended Question Answering | 1 | 8.33% |
BIG-bench Machine Learning | 1 | 8.33% |
Image Segmentation | 1 | 8.33% |