ITU

Label Likelihood Maximisation: Adapting iris segmentation models using domain adaptation

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

View graph of relations

We propose to use unlabelled eye image data for domain adaptation of an iris segmentation network. Adaptation allows the model to be less reliant on its initial generality. This is beneficial due to the large variance exhibited by eye image data which makes training of robust models difficult. The method uses a label prior in conjunction with network predictions to produce pseudo-labels. These are used in place of ground-truth data to adapt a base model. A fully connected neural network performs the pixel-wise iris segmentation. The base model is trained on synthetic data and adapted to several existing datasets with real-world eye images. The adapted models improve the average pupil centre detection rates by 24% at a distance of 25 pixels. We argue that the proposed method, and domain adaptation in general, is an interesting direction for increasing robustness of eye feature detectors.
Original languageDanish
Title of host publicationETRA '20 Full Papers: ACM Symposium on Eye Tracking Research and Applications
Number of pages9
PublisherAssociation for Computing Machinery
Publication date2020
Pages1-9
Article number5
DOIs
Publication statusPublished - 2020

ID: 85227370