Small size face keypoint detection

[CF2220160244]

When the image infer by the model， the image downsize 4x， the small face is 2-5 pixl in my data ，the keypoint heatmap center is very close, and then After the 3x3 maxpooling, the 5 keypoints may doublication, the 3x3 maxpooling is not suit me, How can i slove the problem, Can you gays give me some advise?

[ywlife]

2-5 pix face is too small, i think you can enlarge the image.