Existing detection or recognition systems typically select one state-of-the-art proposal algorithm to produce massive object-covered candidate windows, and a quality metric specifically designed for this algorithm is utilized to single out small amounts of proposals. However, in practice, the accuracies of different proposal algorithms significantly change from one image content to another one. To obtain more robust proposal results, a generic proposal evaluator (GPE) is highly desired, which could choose optimal candidate windows across multiple proposal algorithms. In this paper, we propose a lazy learning strategy to train the GPE, which aims to blindly estimate the quality of each proposal without accessing to its manual annotation. Unlike the traditional end-to-end framework that learns a universal model from all training samples, we try to build query-specific training subset for each given proposal, where only its ${k}$ -nearest-neighborhoods are collected from all labeled candidate windows. Benefits from the capability of updating the regression parameters for different visual contents, the proposed method delivers a higher quality prediction accuracy even with respect to the deep neural network learned by end-to-end method. Experimental results confirm that the proposed algorithm significantly outperforms many state-of-the-art proposal quality metrics.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Generic Proposal Evaluator: A Lazy Learning Strategy Toward Blind Proposal Quality Assessment


    Contributors:
    Wu, Qingbo (author) / Li, Hongliang (author) / Meng, Fanman (author) / Ngan, King N. (author)


    Publication date :

    2018-01-01


    Size :

    4620198 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Lazy Generic Cuts

    Khandelwal, Dinesh / Bhatia, Kush / Arora, Chetan et al. | British Library Online Contents | 2016


    Lazy Generic Cuts

    Khandelwal, Dinesh / Bhatia, Kush / Arora, Chetan et al. | British Library Online Contents | 2016


    PROPOSAL DEVICE, PROPOSAL METHOD AND PROPOSAL PROGRAM

    WATANABE KOSUKE / TSUBOUCHI KOTA / ICHIEN SHINJI et al. | European Patent Office | 2020

    Free access

    PROPOSAL DEVICE AND PROPOSAL SYSTEM

    SUDO HIROAKI | European Patent Office | 2024

    Free access

    PROPOSAL SYSTEM AND PROPOSAL METHOD

    TSUDA KARIN / YAMASHIRO MASAO / OTSUKA RIEKO | European Patent Office | 2021

    Free access