中大機構典藏-NCU Institutional Repository-提供博碩士論文、考古題、期刊論文、研究計畫等下載:Item 987654321/94223
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 80990/80990 (100%)
Visitors : 42793397      Online Users : 973
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/94223


    Title: 以多模態與In-Training XAI 為基礎之無監督Tiny與Fine-grained特徵分群技術;Multimodel-Based and In-Training Xai for Unsupervised Tiny and Fine-Grained Vi Sual Representation Clustering
    Authors: 林家瑜
    Contributors: 國立中央大學資訊工程學系
    Keywords: 非監督式分類;對比式學習;多模態;解釋性AI;3D特徵擷取;Unsupervised Classification;Contrastive Learning;Multimodel;XAI;3D Feature Extraction
    Date: 2024-09-27
    Issue Date: 2024-09-30 17:20:10 (UTC+8)
    Publisher: 國家科學及技術委員會(本會)
    Abstract: 本計畫將提出一個「Multimodel-based and In-Training XAI for Unsupervised Tiny and Fine-grained Visual Representation Clustering」,將Multimodel與contrastive learning結合,運用輔助圖提升模型關注Tiny重要特徵的能力,除此之外,也嘗試加入In-Training XAI,運用XAI的結果引導模型訓練,強化模型擷取特徵的能力,以達成透過非監督式(unsupervised learning)的方法,讓不同類別的圖片可以分在不同的群中,每一個群的成員大部分或全部是由同一個類別的圖片組成,若群分的好,即可完全無標註就能完成分類的任務。此技術大幅降低需要人工標註資料的問題,不僅前瞻,將可推廣擴散至各產業,大幅提升搜集資料導入AI的效率。
    Relation: 財團法人國家實驗研究院科技政策研究與資訊中心
    Appears in Collections:[Department of Computer Science and information Engineering] Research Project

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML43View/Open


    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明