Aerial images record the dynamic Earth terrain, reflecting changes in land cover patterns caused by natural processes and human activities. Nonetheless, prevailing aerial image classification methodologies predominantly function within a closed-set framework, thereby encountering challenges when confronted with the identification of newly emerging scenes. To address this, this paper explores an aerial image recognition scenario in which a dataset comprises both labeled and unlabeled aerial images, intending to classify all images within the unlabeled subset, termed Generalized Category Discovery (GCD). It is noteworthy that the unlabeled images may pertain to labeled classes or represent novel classes. Specifically, we first develop a contrastive learning framework drawing upon the cutting-edge algorithms in GCD. Based on the multi-object characteristics of aerial images, we then propose a slot attention-based GCD training process (Slot-GCD) that contrasts learning at both the object and image levels. It decouples multiple local object features from feature maps using slots and then reconstructs the overall semantic feature of the image based on slot confidence scores and the feature map. Finally, these object-level and image-level features are input into the contrastive learning module to enable the model to learn more precise image semantic features. Comprehensive evaluations across three public aerial image datasets highlight the superiority of our approach over state-of-the-art methods. Particularly, Slot-GCD achieves a recognition accuracy of 91.5% for known old classes and 81.9% for unknown novel class data on the AID dataset.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Generalized Category Discovery in Aerial Image Classification via Slot Attention


    Beteiligte:
    Yifan Zhou (Autor:in) / Haoran Zhu (Autor:in) / Yan Zhang (Autor:in) / Shuo Liang (Autor:in) / Yujing Wang (Autor:in) / Wen Yang (Autor:in)


    Erscheinungsdatum :

    2024




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    Deep Attention-Based Lightweight Network for Aerial Image Deblurring

    Wang, Suhe / Liu, Bo | British Library Conference Proceedings | 2022


    Iterative Category Discovery via Multiple Kernel Metric Learning

    Galleguillos, C. / McFee, B. / Lanckriet, G. R. | British Library Online Contents | 2014


    Weakly Supervised Image Classification Based on Attention Mechanism

    Cheng, Xiaohui / Liu, Pengfei / Chen, Shouxue | IEEE | 2020


    Learning Multi-category Classification in Bayesian Framework

    Kanaujia, A. / Metaxas, D. | British Library Conference Proceedings | 2006


    Learning Multi-category Classification in Bayesian Framework

    Kanaujia, Atul / Metaxas, Dimitris | Springer Verlag | 2006