A Novel Knowledge-Compatibility Benchmarker for Semantic Segmentation

Abstract

Abstract-The quality of a semantic annotation is typically measured with its averaged class-accuracy value, whose computation requires scarce ground-truth annotations. We observe that humans accumulate knowledge through their vision and believe that the quality of a semantic annotation is proportionally related to its compatibility with the vision-based knowledge. We propose a knowledge-compatibility benchmarker, whose backbone is a regression machine. It takes as input a semantic annotation and the vision-based knowledge, then outputs an estimate of the corresponding averaged class-accuracy value. The knowledge encodes three kinds of information, namely: cooccurrence statistics, scene properties and relative positions. We introduce three types of feature vectors for regression. Each specifies the characteristics of a probability vector that captures the compatibility between an annotation and each kind of the knowledge. Experiment results show that the Gradient Boosting regression outperforms the ν-Support Vector regression. It achieves best performance at an R 2 -score of 0.737 and an MSE of 0.034. This indicates not only that the vision-based knowledge resembles humans' common sense but also that the feature vector for regression is justifiable.

Ellipse Detection on Embryo Imaging Using Random Sample Consensus (Ransac) Method Based on Arc Segment

“…Next, the segmentation results will be assessed by using such a segmentation benchmarker as developed by dewanto et.al. [14]. And at the end of this research will aim to make a telehealth system as in Figure 1.…”