Sparse Shape Encoding for Improved Instance Segmentation

Simple item page
dc.contributor.advisorElder, James
dc.contributor.authorLiu, Keyi
dc.date.accessioned2023-08-04T15:05:06Z
dc.date.available2023-08-04T15:05:06Z
dc.date.issued2023-08-04
dc.date.updated2023-08-04T15:05:05Z
dc.degree.disciplineComputer Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractNeurophysiological studies suggest that neurons in the intermediate visual area V4 of the primate cortex encode a sparse representation of object shape. While there are metabolic arguments for such sparse representations, there are also potential advantages for inference. Here we explore whether sparse shape encoding can yield benefits for instance segmentation. Specifically, we encode 2D object shape using a Distance Transform Map(DTM) and learn a sparse basis for this representation. To make use of this encoding, we design an instance segmentation head to estimate the sparse coefficients of each object, and then recover the shape from the zero-crossing level set of the corresponding DTM. Our novel SparseShape encoding approach produces fewer topological errors than the state-of-the-art, yields competitive mask AP on the MS COCO benchmark, and exhibits superior generalization performance on the Cityscapes traffic instance segmentation task.
dc.identifier.urihttps://hdl.handle.net/10315/41293
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectArtificial intelligence
dc.subjectComputer science
dc.subject.keywordsInstance segmentation
dc.subject.keywordsDeep learning
dc.subject.keywordsShape representation
dc.subject.keywordsSparse coding
dc.subject.keywordsConvolutional neural networks
dc.subject.keywordsDistance transform
dc.titleSparse Shape Encoding for Improved Instance Segmentation
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Liu_Keyi_2023_Masters.pdf
Size:
31 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.