Mask-TS Net: Mask Temperature Scaling Uncertainty Calibration for Polyp Segmentation

arXiv:2405.05830v1 Announce Type: new
Abstract: Lots of popular calibration methods in medical images focus on classification, but there are few comparable studies on semantic segmentation. In polyp segmentation of medical images, we find most diseased area occupies only a small portion of the entire image, resulting in previous models being not well-calibrated for lesion regions but well-calibrated for background, despite their seemingly better Expected Calibration Error (ECE) scores overall. Therefore, we proposed four-branches calibration network with Mask-Loss and Mask-TS strategies …

abstract arxiv calibration classification cs.cv focus image images medical popular scaling segmentation semantic small studies type uncertainty