國立虎尾科技大學 |

A Self-Supervised Approach For Learning Object Detectors From Semi-Annotated Images.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	A Self-Supervised Approach For Learning Object Detectors From Semi-Annotated Images./
作者:	Zhang, Chenlei.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	40 p.
附註:	Source: Masters Abstracts International, Volume: 83-04.
Contained By:	Masters Abstracts International83-04.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28722449
ISBN:	9798544282549

A Self-Supervised Approach For Learning Object Detectors From Semi-Annotated Images.
Zhang, Chenlei.

A Self-Supervised Approach For Learning Object Detectors From Semi-Annotated Images. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 40 p.

Source: Masters Abstracts International, Volume: 83-04.

Thesis (M.Sc.)--San Diego State University, 2021.

This item must not be sold to any third party vendors.

Most of the existing object detection models require large-scale datasets for training. Semi-supervised learning is becoming an important task as it reduces the work of human annotation to get a robust object detection model. The generic semi-supervised learning approach is to train an initial model with a small amount of labeled data, inference the model on unlabeled data to pick up a set of new data(pseudo-labeling data) with high confidence, then train the model again with the initial labeled data and the pseudo-labeling data. Using pseudo-labeling data is one of the best methods to obtain a semi-supervised learning model. However, the initial labeled data is not always balanced and it makes the mean Average Precision (mAP) of the model lower than expected, especially comparing with other fully supervised models. In this paper, we propose a method of generating pseudo-labeling data iteratively by applying knowledge of data distribution to balance the data set and benefit the mAP. It improves the performance of a model with very few labeled examples and outperforms the generic semi-supervised learning method with only one iteration of pseudo-labeling data.

ISBN: 9798544282549Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Semi-supervised learning

A Self-Supervised Approach For Learning Object Detectors From Semi-Annotated Images.
LDR:02216nam a2200325 4500 001 1067248
005 20220823142327.5
008 221020s2021 ||||||||||||||||| ||eng d
020 $a 9798544282549
035 $a (MiAaPQ)AAI28722449
035 $a AAI28722449
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Chenlei. $3 1372728
245 1 0 $a A Self-Supervised Approach For Learning Object Detectors From Semi-Annotated Images.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 40 p.
500 $a Source: Masters Abstracts International, Volume: 83-04.
500 $a Advisor: Liu, Xiabai.
502 $a Thesis (M.Sc.)--San Diego State University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Most of the existing object detection models require large-scale datasets for training. Semi-supervised learning is becoming an important task as it reduces the work of human annotation to get a robust object detection model. The generic semi-supervised learning approach is to train an initial model with a small amount of labeled data, inference the model on unlabeled data to pick up a set of new data(pseudo-labeling data) with high confidence, then train the model again with the initial labeled data and the pseudo-labeling data. Using pseudo-labeling data is one of the best methods to obtain a semi-supervised learning model. However, the initial labeled data is not always balanced and it makes the mean Average Precision (mAP) of the model lower than expected, especially comparing with other fully supervised models. In this paper, we propose a method of generating pseudo-labeling data iteratively by applying knowledge of data distribution to balance the data set and benefit the mAP. It improves the performance of a model with very few labeled examples and outperforms the generic semi-supervised learning method with only one iteration of pseudo-labeling data.
590 $a School code: 0220.
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
653 $a Semi-supervised learning
653 $a Object detection models
690 $a 0984
690 $a 0800
710 2 $a San Diego State University. $b Computer Science. $3 1179359
773 0 $t Masters Abstracts International $g 83-04.
790 $a 0220
791 $a M.Sc.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28722449