Return to Question

So I was studying MobileNetV2 architecture and came across this table, from the original paper, that represents its architecture.

Table Description: "Table 2: MobileNetV2 : Each line describes a sequence of 1 or more identical (modulo stride) layers, repeated n times. All layers in the same sequence have the same number c of output channels. The first layer of each sequence has a stride s and all others use stride 1. All spatial convolutions use 3 × 3 kernels. The expansion factor t is always applied to the input size as described in Table 1."

However I don't really understand why the last pointwise convolution (conv2d 1x1) is applied after the average pooling. Shouldn't the output from the avgpool go to a dense layer so that it can then perform its predictions? What is the point of performing convolution, more precisely pointwise conv. after pooling? Also, why is k not a fixed number of kernels/filters, like the other layers?

Thanks in advance!

So I was studying MobileNetV2 architecture and came across this table from the original paper that represents its architecture:

Table Description: "Table 2: MobileNetV2 : Each line describes a sequence of 1 or more identical (modulo stride) layers, repeated n times. All layers in the same sequence have the same number c of output channels. The first layer of each sequence has a stride s and all others use stride 1. All spatial convolutions use 3 × 3 kernels. The expansion factor t is always applied to the input size as described in Table 1."

However I don't really understand why the last pointwise convolution (conv2d 1x1) is applied after the average pooling. Shouldn't the output from the avgpool go to a dense layer so that it can then perform its predictions? 

What is the point of performing convolution, more precisely pointwise conv. after pooling? Also, why is k not a fixed number of kernels/filters, like the other layers?

Thanks in advance!

So I was studying MobileNetV2 architecture and came across this table, from the original paper, that represents its architecture.

However I don't really understand why the last pointwise convolution (conv2d 1x1) is applied after the average pooling. Shouldn't the output from the avgpool go to a dense layer so that it can then perform its predictions? What is the point of performing convolution, more precisely pointwise conv. after pooling? Also, why is k not a fixed number of kernels/filters, like the other layers?

Thanks in advance!

So I was studying MobileNetV2 architecture and came across this table, from the original paper, that represents its architecture.

Table Description: "Table 2: MobileNetV2 : Each line describes a sequence of 1 or more identical (modulo stride) layers, repeated n times. All layers in the same sequence have the same number c of output channels. The first layer of each sequence has a stride s and all others use stride 1. All spatial convolutions use 3 × 3 kernels. The expansion factor t is always applied to the input size as described in Table 1."

However I don't really understand why the last pointwise convolution (conv2d 1x1) is applied after the average pooling. Shouldn't the output from the avgpool go to a dense layer so that it can then perform its predictions? What is the point of performing convolution, more precisely pointwise conv. after pooling? Also, why is k not a fixed number of kernels/filters, like the other layers?

Thanks in advance!

So I was studying MobileNetV2 architecture and came across this table, from the original paper, that represents its architecture.

Table description: Table 2: MobileNetV2 : Each line describes a sequence of 1 or more identical (modulo stride) layers, repeated n times. All layers in the same sequence have the same number c of output channels. The first layer of each sequence has a stride s and all others use stride 1. All spatial convolutions use 3 × 3 kernels. The expansion factor t is always applied to the input size as described in Table 1.

However I don't really understand why the last pointwise convolution (conv2d 1x1) is applied after the average pooling. Shouldn't the output from the avgpool go to a dense layer so that it can then perform its predictions? What is the point of performing convolution, more precisely pointwise conv. after pooling? Also, why is k not a fixed number of kernels/filters, like the other layers?

Thanks in advance!

So I was studying MobileNetV2 architecture and came across this table, from the original paper, that represents its architecture.

However I don't really understand why the last pointwise convolution (conv2d 1x1) is applied after the average pooling. Shouldn't the output from the avgpool go to a dense layer so that it can then perform its predictions? What is the point of performing convolution, more precisely pointwise conv. after pooling? Also, why is k not a fixed number of kernels/filters, like the other layers?

Thanks in advance!