Show simple item record

dc.contributor.advisorKampffmeyer, Michael C.
dc.contributor.authorBurman, Joel
dc.date.accessioned2022-08-15T15:05:31Z
dc.date.available2022-08-15T15:05:31Z
dc.date.issued2022-06-22
dc.description.abstractFew-shot segmentation has in recent years gotten a lot of attention. The reason is its ability to segment images from classes based on only a handful of labeled support images. This opens up many possibilities when the need for a big dataset is removed. To do this a few-shot segmentation network need to extract as much quality information from each support image as possible. In this thesis we are exploring if an existing few-shot segmentation network can be improved by making the inference phase more target class specific. To do this we are introducing our Inference Guided Few-Shot Segmentation (IGFSS) method. It can be applied to an existing few-shot segmentation network. It changes the inference phase from a static network to one that adapts certain class specific parts of the network to each new target class. We tested our method with the Self-Guided Cross-Guided (SGCG) network as backbone. Here we optimized either the prototypes or the decoder. We used the Pascal dataset to compare the results from both methods. This is done on a fixed list from the dataset to be able to make a fair comparison. In the 5-shot setup, where new classes are segmented based on 5 support images. Here we get a solid improvement when our method is applied to both the prototypes and the decoder. The mean IoU score was increased with 3.7% and 7.5% respectively. The dataset was analysed with regard to image and object distributions. This gives us a better understanding of the results of our IGFSS method. While our IGFSS method does benefit all classes this could be a first step towards a Class-Adaptive Inference Guided Few-Shot Segmentation method.en_US
dc.identifier.urihttps://hdl.handle.net/10037/26200
dc.language.isoengen_US
dc.publisherUiT Norges arktiske universiteten_US
dc.publisherUiT The Arctic University of Norwayen_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2022 The Author(s)
dc.rights.urihttps://creativecommons.org/licenses/by-nc-sa/4.0en_US
dc.rightsAttribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)en_US
dc.subject.courseIDFYS-3941
dc.subjectMachine Learningen_US
dc.subjectFew-shot segmentationen_US
dc.subjectfine tuningen_US
dc.subjectinference phaseen_US
dc.titleInference Guided Few-Shot Segmentationen_US
dc.typeMaster thesisen_US
dc.typeMastergradsoppgaveen_US


File(s) in this item

Thumbnail
Thumbnail

This item appears in the following collection(s)

Show simple item record

Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)