Annotating automatic target recognition (ATR) is a highly challenging task, primarily due to the unavailability of labeled data in the target domain. Hence, it is essential to construct an optimal target domain classifier by utilizing the labeled information of the source domain images. The transductive transfer learning (TTL) method that incorporates a CycleGAN-based unpaired domain translation network has been previously proposed in the literature for effective ATR annotation. Although this method demonstrates great potential for ATR, it severely suffers from lower annotation performance, higher Fréchet inception distance (FID) score, and the presence of visual artifacts in the synthetic images. To address these issues, we propose a hybrid contrastive learning base unpaired domain translation (H-CUT) network that achieves a significantly lower FID score. It incorporates both attention and entropy to emphasize the domain-specific region, a noisy feature mixup module to generate high variational synthetic negative patches, and a modulated noise contrastive estimation (MoNCE) loss to reweight all negative patches using optimal transport for better performance. Our proposed contrastive learning and cycle-consistency-based TTL (C3TTL) framework consists of two H-CUT networks and two classifiers. It simultaneously optimizes cycle-consistency, MoNCE, and identity losses. In C3TTL, two H-CUT networks have been employed through a bijection mapping to feed the reconstructed source domain images into a pretrained classifier to guide the optimal target domain classifier. Extensive experimental analysis conducted on six ATR datasets demonstrates that the proposed C3TTL method is effective in annotating civilian and military vehicles, ships, planes, and human targets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Contrastive Learning and Cycle Consistency-Based Transductive Transfer Learning for Target Annotation


    Beteiligte:


    Erscheinungsdatum :

    01.04.2024


    Format / Umfang :

    7459555 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Rainfall Estimation Using Transductive Learning

    Martins de Freitas, Greice / Heuminski de Ávila, Ana Maria / Papa, João Paulo | IEEE | 2008



    Texture Image Segmentation: An Interactive Framework Based on Adaptive Features and Transductive Learning

    Xiang, S. / Nie, F. / Zhang, C. | British Library Conference Proceedings | 2006



    Class Hierarchy Aware Contrastive Feature Learning for Multigranularity SAR Target Recognition

    Wen, Zaidao / Wang, Zikai / Zhang, Jianting et al. | IEEE | 2024