Re:Graph Convolutional Networks (2016)
by pfd1986 on Tuesday April 23, 2019 @08:42PM
(#19734511)
In a traditional CNN you use the same convolution kernel across an entire image. Here you do the same but you convolve the features of a person (pixel) with the feature of its neighbors, but those change depending on the network. Drawbacks are: I) you add one new person to the network, the whole thing has to be retrained; ii) convolutions are more complex and expensive
[ Parent
| on HN ]
There are no comments on this comment yet.