Empowered by labeled datasets, supervised pre-training based transfer learning (SPTL) has made significant advances for image classification applications. However, due to privacy-preserving protocol and unaccessible annotation, it emerges as a novel problem in federated learning scenarios whether unsupervised pre-training based transfer learning (UPTL) is available for semantic segmentation. In this work, we define federated transfer learning (FedTL) in the absence of source domain label, and track research progress on pavement crack benchmark. The main challenges of FedTL include: i) a privacy-protecting distributed training framework that extends UPTL to the constraints of federated settings, and ii) a self-learning semantic segmentation approach that develops self-supervised learning paradigm to simultaneously learn category and shape representations. Motivated by that, we propose a FedCrack model to absorb feature disentanglement and prototype clustering into vision Transformer, which obtains the pre-trained encoder on source domain without accessing annotation. Thereafter, a fine-tuning stage is presented to learn decoder with scaling attention on target domain for fine-grained crack segmentation. The effectiveness of proposed FedCrack can be demonstrated with superior performance of 82.14% on mIoU and 9.85 FPS on speed in extensive experiments. To the best of our knowledge, it is the first work in FedTL to gain weights of unsupervised pre-training representations on source domain locally, gradients of which are then aggregated to a federated central model that also fine-tunes the transferable parameters by target domain.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    FedCrack: Federated Transfer Learning With Unsupervised Representation for Crack Detection


    Beteiligte:
    Jin, Xiating (Autor:in) / Bu, Jiajun (Autor:in) / Yu, Zhi (Autor:in) / Zhang, Hui (Autor:in) / Wang, Yaonan (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2023-10-01


    Format / Umfang :

    10629979 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Generalizable Journey Mode Detection Using Unsupervised Representation Learning

    Bandyopadhyay, Soma / Datta, Anish / Ramakrishnan, Ramesh Kumar et al. | IEEE | 2024


    Federated Representation Learning With Data Heterogeneity for Human Mobility Prediction

    Zhang, Xiao / Wang, Qilin / Ye, Ziming et al. | IEEE | 2023


    Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning

    Itahara, Sohei / Nishio, Takayuki / Morikura, Masahiro et al. | IEEE | 2020


    Truly Unsupervised Image-to-Image Translation with Contrastive Representation Learning

    Hong, Zhiwei / Feng, Jianxing / Jiang, Tao | British Library Conference Proceedings | 2023


    CURL: Image Classification using co-training and Unsupervised Representation Learning

    Bianco, Simone / Ciocca, Gianluigi / Cusano, Claudio | British Library Online Contents | 2016