What is a good evaluation measure for semantic segmentation?
2013pp. 32.1–32.11
Citations Over TimeTop 10% of 2013 papers
Abstract
In this work, we consider the evaluation of the semantic segmentation task. We discuss the strengths and limitations of the few existing measures, and propose new ways to evaluate semantic segmentation. First, we argue that a per-image score instead of one computed over the entire dataset brings a lot more insight. Second, we propose to take contours more carefully into account. Based on the conducted experiments, we suggest best practices for the evaluation. Finally, we present a user study we conducted to better understand how the quality of image segmentations is perceived by humans.
Related Papers
- → Measure for measure,' II(1895)2 cited
- The Axiomatization Definition of the Pseudo Measure of Fuzziness and the Pseudo Measure of Fuzziness of a Cosine Function(1999)
- Influence of Main Factors in Industry Measurement on Measure Accuracy(2002)
- → "Measure for Measure."(1866)
- → Review: William Shakespeare: Measure for Measure * Kate Chedgzoy: William Shakespeare: Measure for Measure(2002)