Landmark localization

Landmark localization - 예시(facial landmark localization & Human pose estimation)

Predicting the coordinate of keypoints

 

1. Coordinate regression : Usually inaccurate and biased

2. heatmap classification : better performance but high computational cost

 

Hourglass network

stacked hourglass modules allow for repeated bottom-up and top-down inference that refines the output of the previous hourglass module

 

stack을 지날수록 더 refine 하게 추정

이전의 feature map의 결과를 convolution 한 것과 덧셈을 해서 새로운 layer로 활용함

 

UVmap(vector좌표 표기법) is a flattened representation of 3D geometry. Also, UV map is invariant to motion(i.e., cannonical coordinate)

 

DensePose R-CNN = Faster R-CNN + 3D surface regression branch

 

RetinaFace = FPN + Multi-task brances(classification, bounding box, 5 point regression, mesh regression)

동시에 다른 task를 학습하면서 공통된 대상의 다양한특징을 자연스럽게 학습하면서 서로 도와 성능향상을 도모할 수 있다.

 

요즘의 흐름 -> FPN + Target-task brances