Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74045
Title: | 基於軟性排名損失函數之圖像相似度估測 Soft Ranking Losses for Deep Image Similarity Estimation |
Authors: | Chiao-An Yang 楊喬諳 |
Advisor: | 莊永裕(Yung-Yu Chuang) |
Co-Advisor: | 林彥宇(Yen-Yu Lin) |
Keyword: | 深度度量學習,圖像檢索, deep metric learning,image retrieval, |
Publication Year : | 2019 |
Degree: | 碩士 |
Abstract: | 三元子損失函數被廣泛地使用在基於內容的圖像檢索和深度量度學習之中。然而,要達到良好的訓練效果,往往必須反覆實驗已取得最好的超參數。這篇論文使用各個樣本間的排名資訊以解決這項問題。我們是用了排名值的軟性估計,並藉此提出了軟性排名閾值損失函數。我們的損失函數目標在最小化正樣本間的排名值直到其小於某個給定的閾值,同時最大化副樣本間的排名值直到其大於某個給定的閾值。為求更進步的表現,我們提出了一種難例挖掘技巧,藉由推移某些負樣本間的距離已達到更好的訓練效果。我們的實驗顯示,我們的損失函數在行人重識別和衣物檢索上的資料集都打敗了其他損失函數。我們提出的損失函數亦可以被使用在其他圖像檢索的課題上。 Triplet losses have been widely used in content-based image retrieval and deep metric learning. However, it usually suffers the problems of setting some hyper-parameters which require repeated tests. This thesis uses the information of the rank between samples in a single batch to tackle this problem. We introduce the soft ranking threshold loss, which utilizes the soft approximation of such ranking values. Our loss aims to minimize the ranking value of anchor-positive pair to be less than a given threshold and maximize the ranking value of anchor-negative pair to be greater than a given threshold. To further improve the performance of our loss, we also propose a hard mining technique by shifting the distances of anchor-negative pairs. We show that our loss outperforms other losses on both person re-identification and fashion retrieval. The proposed loss can also be applied to other content-based image retrieval tasks. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74045 |
DOI: | 10.6342/NTU201903394 |
Fulltext Rights: | 有償授權 |
Appears in Collections: | 資訊網路與多媒體研究所 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-108-1.pdf Restricted Access | 1.5 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.