no code implementations • 24 Oct 2021 • Yizhe Zhang, Shubhankar Borse, Hong Cai, Ying Wang, Ning Bi, Xiaoyun Jiang, Fatih Porikli
More specifically, by measuring the perceptual consistency between the predicted segmentation and the available ground truth on a nearby frame and combining it with the segmentation confidence, we can accurately assess the classification correctness on each pixel.