Lightweight image segmentation
Deploying advanced image segmentation tasks on mobile devices struggle with the demands of sophisticated deep learning models. Image segmentation, a critical task in computer vision, has seen remarkable advancements through deep learning. However, the implementation of these computationally inten...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/175006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Deploying advanced image segmentation tasks on mobile devices struggle with the
demands of sophisticated deep learning models. Image segmentation, a critical task in
computer vision, has seen remarkable advancements through deep learning. However,
the implementation of these computationally intensive models on mobile devices is
hindered by their large size and resource demands. The project aims to develop a
mobile-friendly, lightweight deep learning architecture for image segmentation, drawing inspiration from DeepLabV3’s capabilities. The goal is to balance the trade-off
between accuracy and speed, thereby making advanced image segmentation feasible
on mobile platforms. |
|---|