Incorporating Metadata for Semantic Segmentation by employing Channel Attention Mechanism

Показати скорочений опис матеріалу

dc.contributor.author Plutenko, Iaroslav
dc.date.accessioned 2021-06-29T14:08:31Z
dc.date.available 2021-06-29T14:08:31Z
dc.date.issued 2021
dc.identifier.citation Plutenko, Iaroslav. Incorporating Metadata for Semantic Segmentation by employing Channel Attention Mechanism / Iaroslav Plutenko; Supervisor: Dmytro Fishman; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2021. – 58 p.: ill. uk
dc.identifier.uri https://er.ucu.edu.ua/handle/1/2704
dc.description.abstract The meta-information accompanying data from image acquisition devices has limited use in microscopy image processing techniques involving Deep Learning. This project aims to incorporate the supplementary metadata for semantic segmentation by employing a channel selection mechanism in convolutional networks outlining its potential benefits and practical applications where metadata can be used for switching tasks within a master model. The results of conducted experiments show that meta-information is helpful, and the phenomenon is more expressed with incompatible segmentation tasks, where a multi-head model or separate models are required otherwise. Overall, we have achieved a slight increase in scores for similar tasks as well and demonstrated the applicability of the CNN model for separate tasks, forcing it to work as an ensemble, leveraging the beneficial effect of multi-task learning. uk
dc.language.iso en uk
dc.subject semantic segmentation task uk
dc.subject Channel Attention Mechanism uk
dc.title Incorporating Metadata for Semantic Segmentation by employing Channel Attention Mechanism uk
dc.type Preprint uk
dc.status Публікується вперше uk


Долучені файли

Даний матеріал зустрічається у наступних зібраннях

Показати скорочений опис матеріалу

Пошук


Перегляд

Мій обліковий запис