Please use this identifier to cite or link to this item:
Title: Instance LSeg - exploring instance level information from visual language model
Authors: Lin, Zixing
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2023
Publisher: Nanyang Technological University
Source: Lin, Z. (2023). Instance LSeg - exploring instance level information from visual language model. Final Year Project (FYP), Nanyang Technological University, Singapore.
Abstract: This final year project explores the potential of using large-scale pretrained visual language models in instance-level zero-shot computer vision tasks. Specifically, we propose Instance LSeg - a novel approach to extend the zero-shot semantic segmentation method LSeg to perform language guided instance segmentation and grounding of natural language expressions in images. To evaluate our method, we used three popular referring datasets, and we observe that our method achieves highly competitive results against published generalized visual grounding baselines
Schools: School of Computer Science and Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
Undergraduate project report1.9 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 15, 2024


Updated on Jun 15, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.