This technique factorizes a standard convolutional layer into a depthwise convolution and a pointwise convolution. Depthwise convolution applies a filter to each input channel separately, while pointwise convolution applies a 1x1 convolution to combine the outputs. This factorization significantly reduces the number of parameters and computational cost.
The “Patched” suffix refers to a . Instead of resizing the entire frame to 224×224, the model: moviesmobilenet patched