Mirror segmentation is an emerging computer vision task that is extensively applied in various fields. However, it presents significant challenges to existing segmentation methods when irregular shapes are involved. Most methods are designed for deployment on heavy-duty host machines that demand substantial computational resources and storage capacity, which limits their feasibility for deployment on mobile devices, where efficient and resource-friendly solutions are required. Therefore, we propose a morphology-guided network (MGNet) with knowledge distillation, called MGNet-S*, to achieve the efficiency required for deployment in mobile devices. In this network, we introduce an erosion dilation fusion module that leverages morphological knowledge to extract texture details from intrinsic features. This module incorporates different optimization strategies for multimodal features. Furthermore, it provides a knowledge-distillation framework specifically tailored to the proposed MGNet-S*. The MGNet-S* includes three effective distillation modules: a semi-soft label, misaligned features, and adaptive aggregation types. These modules facilitate the efficient transfer of knowledge from the MGNet teacher to MGNet student, allowing the lightweight network, MGNet-S*, to achieve remarkable performance. Numerous experiments proved that our proposed MGNet-S* outperformed state-of-the-art methods, achieving an 88.6% reduction in parameter count and 82.5% reduction in floating-point operations compared to those of the MGNet teacher network.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Morphology-Guided Network via Knowledge Distillation for RGB-D Mirror Segmentation


    Beteiligte:
    Zhou, Wujie (Autor:in) / Cai, Yuqi (Autor:in) / Qiang, Fangfang (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.11.2024


    Format / Umfang :

    20343014 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation

    Liu, Ruiping / Yang, Kailun / Roitberg, Alina et al. | IEEE | 2024


    Knowledge-Guided Segmentation of 3D Imagery

    Ezquerra, N. / Mullick, R. | British Library Online Contents | 1996


    KNOWLEDGE DISTILLATION TECHNIQUES

    MALACH ERAN / KAPLUN GAL / SHALEV-SHWARTZ SHAI | Europäisches Patentamt | 2023

    Freier Zugriff

    Decoupled Knowledge Distillation

    Zhao, Borui / Cui, Quan / Song, Renjie et al. | ArXiv | 2022

    Freier Zugriff