when the dimensions increase

[binLearning]

Hello everyone.
When the dimensions increase, there are two options: (A) extra zero entries padded for increasing dimensions; (B) use 1×1 convolutions to match dimensions. For both options they are performed with a stride of 2.
I'm confused that decreasing in spatial size is handled by using stride 2 (kernel size 1x1) convolutions will lose 75% of the information.
Wouldn't a max/average-pooling or convolution layer of kernel(2x2) and stride(2x2) maintain more information?

Any help whatsoever is valuable.

[taylorjacklespriggs]

I am also confused about this. From the paper: Downsampling is performed by conv3_1, conv4_1, and conv5_1 with a stride of 2 But this will skip 75% of the conv2, conv3, and conv4 output for the 50, 101, and 152 layer implementations.