Semantic perception in driving scenarios plays a crucial role in intelligent transportation systems. However, existing Transformer-based semantic segmentation methods often do not fully exploit their potential in understanding driving scene dynamically. These methods typically lack spatial reasoning, failing to effectively correlate image pixels with their spatial positions, leading to attention drift. To address this issue, we propose a novel architecture, the Hierarchical Spatial Perception Transformer (HSPFormer), which integrates monocular depth estimation and semantic segmentation into a unified framework for the first time. We introduce the Spatial Depth Perception Auxiliary Network (SDPNet), a framework for multiscale feature extraction and multilayer depth map prediction to establish hierarchical spatial coherence. Additionally, we design the Hierarchical Pyramid Transformer Network (HPTNet), which uses depth estimation as learnable position embeddings to form spatially correlated semantic representations and generate global contextual information. Experiments on benchmark datasets such as KITTI-360, Cityscapes, and NYU Depth V2, demonstrate that HSPFormer outperforms several state-of-the-art networks, and achieves promising performance with 66.82% top-1 mIoU on KITTI-360, 83.8% mIoU on Cityscapes, and 57.7% mIoU on NYU Depth V2, respectively. The code will be made publicly available at https://github.com/SY-Ch/HSPFormer.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation


    Beteiligte:
    Chen, Siyu (Autor:in) / Han, Ting (Autor:in) / Zhang, Changshe (Autor:in) / Su, Jinhe (Autor:in) / Wang, Ruisheng (Autor:in) / Chen, Yiping (Autor:in) / Wang, Zongyue (Autor:in) / Cai, Guorong (Autor:in)


    Erscheinungsdatum :

    01.04.2025


    Format / Umfang :

    5086133 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    TransRVNet: LiDAR Semantic Segmentation With Transformer

    Cheng, Hui-Xian / Han, Xian-Feng / Xiao, Guo-Qiang | IEEE | 2023


    Robust Environmental Perception of Semantic Segmentation

    Pan, Huihui / Wang, Jue / Yu, Xinghu et al. | Springer Verlag | 2023




    TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation

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