Conference Paper/Proceeding/Abstract 255 views
Active Anchors
,
Xianghua Xie
Companion Proceedings of the 2023 ACM SIGCHI Symposium on Engineering Interactive Computing Systems
Swansea University Authors:
Connor Clarkson, Mike Edwards , Xianghua Xie
Full text not available from this repository: check for access using links below.
DOI (Published version): 10.1145/3596454.3597185
Abstract
Defect detection in steel manufacturing has achieved state-of-the art results in both localisation and classification of various types of defects, however, this assumes very high-quality datasets that havebeen verified by domain experts. Labelling such data has become a time-consuming and interactio...
| Published in: | Companion Proceedings of the 2023 ACM SIGCHI Symposium on Engineering Interactive Computing Systems |
|---|---|
| ISBN: | 9798400702068 |
| Published: |
New York, NY, USA
ACM
2023
|
| Online Access: |
http://dx.doi.org/10.1145/3596454.3597185 |
| URI: | https://cronfa.swan.ac.uk/Record/cronfa63777 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract: |
Defect detection in steel manufacturing has achieved state-of-the art results in both localisation and classification of various types of defects, however, this assumes very high-quality datasets that havebeen verified by domain experts. Labelling such data has become a time-consuming and interaction-heavy task with a great amount of user effort, this is due to variability in the defect characteristics andcomposite nature. We propose a new acquisition function based on the similarity of defects for refining labels over time by showing the user only the most required to be labelled. We also explore different ways in which to feed these new refinements back into the model to utilize the new knowledge in an effortful way. We achieve this with a graphical interface that provides additional information to the domain expert as the data gets refined, allowing for decision-making with uncertain areas of the steel. |
|---|---|
| Keywords: |
Human-Centered AI, Active Learning, Data Refinement, Interactive |
| College: |
Faculty of Science and Engineering |
| Funders: |
EPSRC Centre for Doctoral Training in Enhancing Human Interactions and Collaborations with Data and Intelligence Driven Systems |