An Analysis on Samples Selections with Various Confident Levels for Vanilla Pseudo-labeling
碩士 === 國立中山大學 === 電機工程學系研究所 === 107 === In recent years, deep learning become a very popular research topic. Especially, neural networks have made a successful application in target detection. Its accuracy rate has been catching up with humans or better than humans. The algorithm chosen for this...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/4w3264 |
id |
ndltd-TW-107NSYS5442036 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107NSYS54420362019-09-17T03:40:10Z http://ndltd.ncl.edu.tw/handle/4w3264 An Analysis on Samples Selections with Various Confident Levels for Vanilla Pseudo-labeling 訓練資料集自我擴增問題之分析-以YOLO分類器為例 Bor-Hon Tu 杜柏宏 碩士 國立中山大學 電機工程學系研究所 107 In recent years, deep learning become a very popular research topic. Especially, neural networks have made a successful application in target detection. Its accuracy rate has been catching up with humans or better than humans. The algorithm chosen for this paper is YOLO because of its special feature, only using one convolutional neural network to finish image tracking. The prediction performance of convolutional neural network is not only related to the architecture of algorithm design, but also influenced by the data set for training. More importantly, the training set required for image tracking is not only pictures, but also the coordinate position of the target. Traditionally, this type of training set is artificially produced. but in this thesis, the predictions made on other online videos back are directly put into the training set to augment the training materials and retrain them, then collect and re-organize the forecast data of their new weights. Hopefully, the YOLO development of this thesis results in worth reference for other application. Kao-Shing Hwang 黃國勝 2019 學位論文 ; thesis 68 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中山大學 === 電機工程學系研究所 === 107 === In recent years, deep learning become a very popular research topic. Especially, neural networks have made a successful application in target detection. Its accuracy rate has been catching up with humans or better than humans. The algorithm chosen for this paper is YOLO because of its special feature, only using one convolutional neural network to finish image tracking. The prediction performance of convolutional neural network is not only related to the architecture of algorithm design, but also influenced by the data set for training. More importantly, the training set required for image tracking is not only pictures, but also the coordinate position of the target. Traditionally, this type of training set is artificially produced. but in this thesis, the predictions made on other online videos back are directly put into the training set to augment the training materials and retrain them, then collect and re-organize the forecast data of their new weights. Hopefully, the YOLO development of this thesis results in worth reference for other application.
|
author2 |
Kao-Shing Hwang |
author_facet |
Kao-Shing Hwang Bor-Hon Tu 杜柏宏 |
author |
Bor-Hon Tu 杜柏宏 |
spellingShingle |
Bor-Hon Tu 杜柏宏 An Analysis on Samples Selections with Various Confident Levels for Vanilla Pseudo-labeling |
author_sort |
Bor-Hon Tu |
title |
An Analysis on Samples Selections with Various Confident Levels for Vanilla Pseudo-labeling |
title_short |
An Analysis on Samples Selections with Various Confident Levels for Vanilla Pseudo-labeling |
title_full |
An Analysis on Samples Selections with Various Confident Levels for Vanilla Pseudo-labeling |
title_fullStr |
An Analysis on Samples Selections with Various Confident Levels for Vanilla Pseudo-labeling |
title_full_unstemmed |
An Analysis on Samples Selections with Various Confident Levels for Vanilla Pseudo-labeling |
title_sort |
analysis on samples selections with various confident levels for vanilla pseudo-labeling |
publishDate |
2019 |
url |
http://ndltd.ncl.edu.tw/handle/4w3264 |
work_keys_str_mv |
AT borhontu ananalysisonsamplesselectionswithvariousconfidentlevelsforvanillapseudolabeling AT dùbǎihóng ananalysisonsamplesselectionswithvariousconfidentlevelsforvanillapseudolabeling AT borhontu xùnliànzīliàojízìwǒkuòzēngwèntízhīfēnxīyǐyolofēnlèiqìwèilì AT dùbǎihóng xùnliànzīliàojízìwǒkuòzēngwèntízhīfēnxīyǐyolofēnlèiqìwèilì AT borhontu analysisonsamplesselectionswithvariousconfidentlevelsforvanillapseudolabeling AT dùbǎihóng analysisonsamplesselectionswithvariousconfidentlevelsforvanillapseudolabeling |
_version_ |
1719251368221343744 |