Scaling object detection by transferring learning

More and more datasets have increased their size with enough class annotations. Although the classification datasets are easy to collect, a large number of bounding box annotations require significant human labor and it is time-consuming. Thus, the number of bounding box annotations are usually smal...

Full description

Saved in:
Bibliographic Details
Main Author: Liu, Yizheng
Other Authors: Tan Yap Peng
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2020
Subjects:
Online Access:https://hdl.handle.net/10356/140699
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-140699
record_format dspace
spelling sg-ntu-dr.10356-1406992023-07-04T16:29:15Z Scaling object detection by transferring learning Liu, Yizheng Tan Yap Peng School of Electrical and Electronic Engineering EYPTan@ntu.edu.sg Engineering::Electrical and electronic engineering More and more datasets have increased their size with enough class annotations. Although the classification datasets are easy to collect, a large number of bounding box annotations require significant human labor and it is time-consuming. Thus, the number of bounding box annotations are usually small. The supervised training method not only requires image-level classification labels but also needs object-level annotations in the detection database which limit the number of object classes they can detect. Therefore, the weakly-supervised training methods are applied in this experiment in which the weights of the classification network are transferred to the weights of the detection network. We call this an effective and efficient network weight transfer network (WTN). The classification weight is pre-trained by Open Images v2. The detection network and WTN are trained by Objects 365 dataset which is the large-scale object detection dataset and works well in feature learning. The experimental results show that the performance of WTN is improved. Master of Science (Signal Processing) 2020-06-01T07:53:33Z 2020-06-01T07:53:33Z 2020 Thesis-Master by Coursework https://hdl.handle.net/10356/140699 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
spellingShingle Engineering::Electrical and electronic engineering
Liu, Yizheng
Scaling object detection by transferring learning
description More and more datasets have increased their size with enough class annotations. Although the classification datasets are easy to collect, a large number of bounding box annotations require significant human labor and it is time-consuming. Thus, the number of bounding box annotations are usually small. The supervised training method not only requires image-level classification labels but also needs object-level annotations in the detection database which limit the number of object classes they can detect. Therefore, the weakly-supervised training methods are applied in this experiment in which the weights of the classification network are transferred to the weights of the detection network. We call this an effective and efficient network weight transfer network (WTN). The classification weight is pre-trained by Open Images v2. The detection network and WTN are trained by Objects 365 dataset which is the large-scale object detection dataset and works well in feature learning. The experimental results show that the performance of WTN is improved.
author2 Tan Yap Peng
author_facet Tan Yap Peng
Liu, Yizheng
format Thesis-Master by Coursework
author Liu, Yizheng
author_sort Liu, Yizheng
title Scaling object detection by transferring learning
title_short Scaling object detection by transferring learning
title_full Scaling object detection by transferring learning
title_fullStr Scaling object detection by transferring learning
title_full_unstemmed Scaling object detection by transferring learning
title_sort scaling object detection by transferring learning
publisher Nanyang Technological University
publishDate 2020
url https://hdl.handle.net/10356/140699
_version_ 1772826610317131776