DAH: Domain Adapted Deep Image Hashing

Pei Jung Lu, Pao Yun Ma, Ying Ying Chang, Mei Chen Yeh

研究成果: 書貢獻/報告類型會議論文篇章

摘要

With abundant labeled data, deep hashing methods have shown great success in image retrieval. However, these methods are often less powerful when applied to novel datasets. In this paper, we apply unsupervised domain adaptation techniques to improve a state-of-the-art deep hashing method, used in a cross-domain scenario where the model is trained with labeled source data and is evaluated with target data. Experiments show that the generalization capability of a supervised hashing method can be improved by the applied domain adaptation techniques.

原文英語
主出版物標題ISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems
主出版物子標題5G Dream to Reality, Proceeding
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665419512
DOIs
出版狀態已發佈 - 2021
事件2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021 - Hualien, 臺灣
持續時間: 2021 11月 162021 11月 19

出版系列

名字ISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems: 5G Dream to Reality, Proceeding

會議

會議2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021
國家/地區臺灣
城市Hualien
期間2021/11/162021/11/19

ASJC Scopus subject areas

  • 人工智慧
  • 電腦網路與通信
  • 訊號處理
  • 安全、風險、可靠性和品質

指紋

深入研究「DAH: Domain Adapted Deep Image Hashing」主題。共同形成了獨特的指紋。

引用此