Viet-Anh on Software Logo

What is: Sample Redistribution?

SourceSample and Computation Redistribution for Efficient Face Detection
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Sample Redistribution is a data augmentation technique for face detection which augments training samples based on the statistics of benchmark datasets via large-scale cropping. During training data augmentation, square patches are cropped from the original images with a random size from the set [0.3,1.0][0.3,1.0] of the short edge of the original images. To generate more positive samples for stride 8, the random size range is enlarged from [0.3,1.0][0.3,1.0] to [0.3,2.0][0.3,2.0]. When the crop box is beyond the original image, average RGB values fill the missing pixels.

The motivation is that for efficient face detection under a fixed VGA resolution (i.e. 640×480), most of the faces (78.93%) in WIDER FACE are smaller than 32×32 pixels, and thus they are predicted by shallow stages. To obtain more training samples for these shallow stages, Sample Redistribution (SR) is used.