Skip to main content

Incorporation Of Rejection Criterion - A Novel Technique For Evaluating Semantic Segmentation Systems

Mohamed, Elhassan, Sirlantzis, Konstantinos, Howells, Gareth (2021) Incorporation Of Rejection Criterion - A Novel Technique For Evaluating Semantic Segmentation Systems. In: 2021 14th International Conference on Human System Interaction (HSI). . IEEE ISBN 978-1-66544-112-4. (doi:10.1109/HSI52170.2021.9538787) (KAR id:88514)

PDF Author's Accepted Manuscript
Language: English


Download (375kB) Preview
[thumbnail of Incorporation Of Rejection Criterion - A NovelTechnique For Evaluating Semantic Segmentation(ACCEPTED).pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL
http://dx.doi.org/10.1109/HSI52170.2021.9538787

Abstract

Semantic segmentation `SS' evaluation metrics are great tools to assess systems' performance in terms of pixels' accuracy and the alignment of segments. Standard metrics ignore pixels' confidence scores which can carry useful information. Pixels' scores represent the level of confidence of the system for assigning class labels to image pixels. However, it has not been utilised by any evaluating metric for semantic segmentation systems. We propose to incorporate pixels' confidence scores with existing metrics to gain better insights into systems' behaviours. Results show the usefulness of the introduced approach to utilise the pixels' scores in the evaluation process. Besides, using pixels' scores thresholding can help to enhance the system performance on a specific task or objects of a particular size.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.1109/HSI52170.2021.9538787
Projects: [UNSPECIFIED] ADAPT
Uncontrolled keywords: Convolutional Neural Network, Evaluation metrics, Pixels classification, Semantic segmentation, Thresholding
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > TK5101 Telecommunications > TK5102.9 Signal processing
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts
Depositing User: Elhassan Mohamed
Date Deposited: 02 Jun 2021 22:33 UTC
Last Modified: 11 Feb 2022 16:15 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/88514 (The current URI for this page, for reference purposes)
Mohamed, Elhassan: https://orcid.org/0000-0001-9746-1564
Sirlantzis, Konstantinos: https://orcid.org/0000-0002-0847-8880
Howells, Gareth: https://orcid.org/0000-0001-5590-0880
  • Depositors only (login required):

Downloads

Downloads per month over past year