Please use this identifier to cite or link to this item:
Title: Elementwise overparameterisation for single and multi-task learning
Authors: Ribli, Vincent
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Ribli, V. (2022). Elementwise overparameterisation for single and multi-task learning. Final Year Project (FYP), Nanyang Technological University, Singapore.
Abstract: In the field of autonomous vehicles, computer vision is used to solve multiple tasks such as semantic segmentation and object tracking. This can be challenging as the tasks need to be done at a high performance within a given latency threshold. Furthermore, multiple tasks need to be solved simultaneously within the given constraints. To solve such an issue, methods such as overparameterisation, along with multi-task learning, have been proposed. This paper proposes a novel overparameterisation technique, along with a few training tricks, which achieves empirically superior performance compared to existing approaches. These ideas are firstly tested on the CIFAR-100 dataset, which is a single-task problem performing image classification. The ideas are further tested on a multi-task setting using the NYUv2 dataset, performing semantic segmentation, depth estimation and surface normals estimation simultaneously. The results of experimentation have shown promising results through the novel overparameterisation approach, and it is hoped that this overparameterisation technique can generalise well to other architectures and datasets as a simple, yet effective approach to improve performance of deep learning models.
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 
FYP Report_Vincent Ribli.pdf
  Restricted Access
6 MBAdobe PDFView/Open

Page view(s)

Updated on Feb 26, 2024


Updated on Feb 26, 2024

Google ScholarTM


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