Most of the current state-of-the-art frameworks for cross- season visual place recognition (CS-VPR) focus on domain adaptation (DA) to a single specific season. From the viewpoint of long-term CS-VPR, such frameworks do not scale well to sequential multiple domains (e.g., spring → summer → autumun → winter → ⋯). The goal of this study is to develop a novel long-term ensemble learning (LEL) framework that allows for a constant cost retraining in long- term sequential-multi-domain CS-VPR (SMD-VPR), which only requires the memorization of a small constant number of deep convolutional neural networks (CNNs) and can retrain the CNN ensemble of every season at a small constant time/space cost. We frame our task as the multi-teacher multi-student knowledge distillation (MTMS-KD), which re- cursively compresses all the previous season’s knowledge into a current CNN ensemble. We further address the issue of teacher-student-assignment (TSA) to achieve a good general- ization/specialization tradeoff. Experimental results on SMD- VPR tasks validate the efficacy of the proposed approach.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Long-Term Knowledge Distillation of Visual Place Classifiers


    Beteiligte:
    Tomoe, Hiroki (Autor:in) / Kanji, Tanaka (Autor:in)


    Erscheinungsdatum :

    2019-10-01


    Format / Umfang :

    2121143 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Learning and Calibrating Per-Location Classifiers for Visual Place Recognition

    Gronát, P. / Sivic, J. / Obozinski, G. et al. | British Library Online Contents | 2016


    Neural classifiers for automated visual inspection

    Pham, D.T. | Online Contents | 1994


    Neural Classifiers for Automated Visual Inspection

    Pham, D T / Bayro-Corrochano, E J | SAGE Publications | 1994


    Neural classifiers for automated visual inspection

    Pham,D.T. / Byro-Corrochano,E.J. / Univ.of Wales,College of Cardiff,School of Electrical, Electronic and Systems Engng.,GB | Kraftfahrwesen | 1994


    Visual Place Recognition in Long-term and Large-scale Environment based on CNN Feature

    Zhu, Jianliang / Ai, Yunfeng / Tian, Bin et al. | IEEE | 2018