A novel knowledge-compatibility benchmarker for semantic segmentation

Vektor Dewanto, Aprinaldi, Zulfikar Ian, Wisnu Jatmiko

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

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 n-Support Vector regression. It achieves best performance at an R2-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.

Original languageEnglish
Pages (from-to)1284-1312
Number of pages29
JournalInternational Journal on Smart Sensing and Intelligent Systems
Volume8
Issue number2
DOIs
Publication statusPublished - 1 Jan 2015

Keywords

  • Averaged class accuracy
  • Knowledge-compatibility benchmarker
  • Regression
  • Semantic segmentation
  • Vision-based knowledge

Fingerprint Dive into the research topics of 'A novel knowledge-compatibility benchmarker for semantic segmentation'. Together they form a unique fingerprint.

Cite this