<ul data-eligibleForWebStory="true"><li>Selective prediction in semantic segmentation involves the use of a confidence score function to allow models to abstain from offering unreliable predictions.</li><li>A new confidence score function, Soft Dice Confidence (SDC), is proposed for binary semantic segmentation, aligning directly with the Dice coefficient metric without needing tuning or additional held-out data.</li><li>The SDC is shown to be near optimal under conditional independence, with upper and lower bounds established on its performance compared to the ideal confidence score function.</li><li>Experiments on various datasets validate the effectiveness of SDC, surpassing all prior confidence estimators without the requirement of extra data, making it a robust and efficient tool for selective prediction in semantic segmentation.</li></ul>

Soft Dice Confidence: A Near-Optimal Confidence Estimator for Selective Prediction in Semantic Segmentation

Discover more