CLIP for point cloud understanding

Simple item page
dc.contributor.authorGhose, Shuvozit
dc.contributor.examiningcommitteeLivi, Lorenzo (Computer Science)
dc.contributor.examiningcommitteeKai-Sang Leung, Carson (Computer Science)
dc.contributor.supervisorWang, Yang
dc.date.accessioned2023-08-02T16:47:14Z
dc.date.available2023-08-02T16:47:14Z
dc.date.issued2023-08-01
dc.date.submitted2023-08-02T02:07:56Zen_US
dc.degree.disciplineComputer Scienceen_US
dc.degree.levelMaster of Science (M.Sc.)
dc.description.abstractContrastive Vision-Language Pre-training (CLIP) based point cloud classification model has added a new direction in the point cloud classification research domain. In this thesis, we propose two novel methods for CLIP-based point cloud classification. First, we propose a Pretrained Point Cloud to Image Translation Network (PPCITNet) that produces generalized colored images along with additional salient visual cues to the point cloud depth maps for CLIP based point cloud classification. In addition, we propose a novel viewpoint adapter that combines the view feature processed by each viewpoint as well as the global intertwined knowledge that exists across the multi-view features. Next, we propose a novel meta-episodic learning framework for CLIP-based point cloud classification. In addition, we introduce dynamic task sampling within the episode based on performance memory. The experimental results demonstrate the superior performance of the proposed model over existing state-of-the-art CLIP-based models on ModelNet10, ModelNet40, and ScanobjectNN datasets.
dc.description.noteOctober 2023
dc.identifier.urihttp://hdl.handle.net/1993/37441
dc.language.isoeng
dc.rightsopen accessen_US
dc.subjectCLIP
dc.subjectPoint Cloud understanding
dc.subjectMeta Learning
dc.subjectFew shot classification
dc.subjectContrastive Language-Image Pre-Training
dc.subjectPoint Cloud to Image Translation
dc.titleCLIP for point cloud understanding
dc.typemaster thesisen_US
local.subject.manitobano
project.funder.nameUniversity of Manitoba
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Shuvozit_Ghose_M_Sc__Thesis.pdf
Size:
1.09 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
770 B
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
FGS - Electronic Theses and Practica