政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/137243
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 115256/146303 (79%)
造訪人次 : 54501299      線上人數 : 326
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧：
  • 您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料
    •  進階搜尋


    請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/137243


    題名: Virtual Adversarial Active Learning
    作者: 游勤葑
    Yu, Chin-Feng
    Pao, Hsing-Kuo
    貢獻者: 資碩計一
    關鍵詞: Active Learning;Adversarial Examples;Virtual Adversarial Training;Adversarial Training
    日期: 2020-12
    上傳時間: 2021-09-22 13:33:32 (UTC+8)
    摘要: In traditional active learning, one of the most well-known strategies is to select the most uncertain data for annotation. By doing that, we acquire as most as we can obtain from the labeling oracle so that the training in the next run can be much more effective than the one from this run once the informative labeled data are added to training. The strategy however, may not be suitable when deep learning become one of the dominant modeling techniques. Deep learning is notorious for its failure to achieve a certain degree of effectiveness under the adversarial environment. Often we see the sparsity in deep learning training space which gives us a result with low confidence. Moreover, to have some adversarial inputs to fool the deep learners, we should have an active learning strategy that can deal with the aforementioned difficulties. We propose a novel Active Learning strategy based on Virtual Adversarial Training (VAT) and the computation of local distributional roughness (LDR). Instead of selecting the data that are closest to the decision boundaries, we select the data that are located in a place with rough enough surface if measured by the posterior probability. The proposed strategy called Virtual Adversarial Active Learning (VAAL) can help us to find the data with rough surface, reshape the model with smooth posterior distribution output thanks to the active learning framework. Moreover, we shall prefer the labeling data that own enough confidence once they are annotated from an oracle. In VAAL, we have the VAT that can not only be used as a regularization term but also helps us effectively and actively choose the valuable samples for active learning labeling. Experiment results show that the proposed VAAL strategy can guide the convolutional networks model converging efficiently on several well-known datasets.
    關聯: 2020 IEEE International Conference on Big Data (Big Data), Georgia Institute of Technology, USA, Univ of Illinois at Urbana-Champaign, USA, pp.Page(s):5323 - 5331
    資料類型: conference
    DOI 連結: https://doi.org/10.1109/BigData50022.2020.9378021
    DOI: 10.1109/BigData50022.2020.9378021
    顯示於類別:[資訊科學系碩士在職專班] 會議論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    24.pdf1168KbAdobe PDF2362檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋