Show simple item record

dc.contributor.authorSingha, Tanmay
dc.contributor.supervisorAneesh Krishnaen_US
dc.contributor.supervisorSonny Phamen_US
dc.date.accessioned2023-10-31T01:26:45Z
dc.date.available2023-10-31T01:26:45Z
dc.date.issued2023en_US
dc.identifier.urihttp://hdl.handle.net/20.500.11937/93644
dc.description.abstract

This thesis focuses on developing lightweight semantic segmentation models tailored for resource-constrained applications, effectively balancing accuracy and computational efficiency. It introduces several novel concepts, including knowledge sharing, dense bottleneck, and feature re-usability, which enhance the feature hierarchy by capturing fine-grained details, long-range dependencies, and diverse geometrical objects within the scene. To achieve precise object localization and improved semantic representations in real-time environments, the thesis introduces multi-stage feature aggregation, feature scaling, and hybrid-path attention methods.

en_US
dc.publisherCurtin Universityen_US
dc.titleEfficient Semantic Segmentation for Resource-Constrained Applications with Lightweight Neural Networksen_US
dc.typeThesisen_US
dcterms.educationLevelPhDen_US
curtin.departmentSchool of Electrical Engineering, Computing and Mathematical Sciencesen_US
curtin.accessStatusOpen accessen_US
curtin.facultyScience and Engineeringen_US
curtin.contributor.orcidSingha, Tanmay [0000-0001-6924-057X]en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record