search

dvlab-research / PanopticFCN

Fully Convolutional Networks for Panoptic Segmentation (CVPR2021 Oral)
Apache License 2.0
391 stars 53 forks source link

The purpose of embed_extractor in the thing/stuff_generator class #38

Closed Dwrety closed 2 years ago

Dwrety commented 2 years ago

Is it just a linear project layer? After acquiring the kernel weights from the KernelHead, I cannot find any activation layer following the layer itself. The weight seems to go directly to another Conv2d layer (embed_extractor) without any non-linearlity. If so, why not directly producing the kernels in the kernelhead instead?

yanwei-li commented 2 years ago

Hi, the embed_extractor is used to ensure the same channel of the generated kernel and that in the encoded feature. Because the channel in encoded feature may change in different settings. So, the embed_extractor is adopted for adjustment.

Dwrety commented 2 years ago

I see, so it is basically a linear projection. Thanks for your clarification.