In the landscape of autonomous driving, Bird's-Eye-View (BEV) representation has recently garnered substantial attention, serving as a transformative framework for the fusion of multi-modal sensor inputs. The BEV paradigm effectively shifts the sensor fusion challenge from a rulebased methodology to a data-centric approach, thereby facilitating more nuanced feature extraction from an array of heterogeneous sensors. Notwithstanding its evident merits, the computational overhead associated with BEV-based techniques often mandates high-capacity hardware infrastructure, thus posing challenges for practical, real-world implementations. To mitigate this limitation, we introduce a novel contentaware multi-modal joint input pruning technique. Our method leverages BEV as a shared anchor to algorithmically identify and eliminate non-essential sensor regions prior to their introduction into the perception model's backbone. We validate the efficacy of our approach through extensive experiments on the NuScenes dataset, demonstrating substantial computational efficiency without sacrificing perception accuracy. To the best of our knowledge, this work represents the first attempt to alleviate the computational burden from the input pruning point.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning Content-Aware Multi-Modal Joint Input Pruning via Birds'-Eye-View Representation


    Beteiligte:
    Li, Yuxin (Autor:in) / Li, Yiheng (Autor:in) / Yang, Xulei (Autor:in) / Yu, Mengying (Autor:in) / Huang, Zihang (Autor:in) / Wu, Xiaojun (Autor:in) / Yeo, Chai Kiat (Autor:in)


    Erscheinungsdatum :

    24.09.2024


    Format / Umfang :

    1475420 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Multi-View Automatic Target Recognition using Joint Sparse Representation

    Haichao Zhang / Nasrabadi, N. M. / Zhang, Y. et al. | IEEE | 2012



    Personalized Context-Aware Multi-Modal Transportation Recommendation

    Chen, Xianda / Zhu, Meixin / Tiu, PakHin et al. | IEEE | 2024


    Depth representation learning and fusion method based on multi-modal trajectory

    CHEN JING / YUAN CHANGWEI / ZHAO JIAO et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Birds-eye-view image generation device, and birds-eye-view image generation method

    TAKAHASHI KOJI / ICHINOSE TADAO | Europäisches Patentamt | 2017

    Freier Zugriff