Selective segmentation with MC Dropout
A U-Net labels every pixel of a pet photo as pet, background or border (the outline). It runs 21 times in your browser: once normally and 20 times with random dropout. Where the 20 dropout runs disagree, the model is unsure and abstains (red). Lower coverage means it answers on fewer pixels but makes fewer mistakes.
Pixel error 8.13% → 2.18% at 80% coverage
Selective mIoU 0.777 → 0.882
Oxford-IIIT Pet, 3,669 test images
Input
Output
pet
background
border
abstained