% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Ahmed:1038039,
      author       = {Ahmed, Soikat Hasan and Finkbeiner, Jan and Neftci, Emre},
      title        = {{A} {H}ybrid {SNN}-{ANN} {N}etwork for {E}vent-based
                      {O}bject {D}etection with {S}patial and {T}emporal
                      {A}ttention},
      publisher    = {arXiv},
      reportid     = {FZJ-2025-01088},
      year         = {2024},
      abstract     = {Event cameras offer high temporal resolution and dynamic
                      range with minimal motion blur, making them promising for
                      object detection tasks. While Spiking Neural Networks (SNNs)
                      are a natural match for event-based sensory data and enable
                      ultra-energy efficient and low latency inference on
                      neuromorphic hardware, Artificial Neural Networks (ANNs)
                      tend to display more stable training dynamics and faster
                      convergence resulting in greater task performance. Hybrid
                      SNN-ANN approaches are a promising alternative, enabling to
                      leverage the strengths of both SNN and ANN architectures. In
                      this work, we introduce the first Hybrid Attention-based
                      SNN-ANN backbone for object detection using event cameras.
                      We propose a novel Attention-based SNN-ANN bridge module to
                      capture sparse spatial and temporal relations from the SNN
                      layer and convert them into dense feature maps for the ANN
                      part of the backbone. Experimental results demonstrate that
                      our proposed method surpasses baseline hybrid and SNN-based
                      approaches by significant margins, with results comparable
                      to existing ANN-based methods. Extensive ablation studies
                      confirm the effectiveness of our proposed modules and
                      architectural choices. These results pave the way toward a
                      hybrid SNN-ANN architecture that achieves ANN like
                      performance at a drastically reduced parameter budget. We
                      implemented the SNN blocks on digital neuromorphic hardware
                      to investigate latency and power consumption and demonstrate
                      the feasibility of our approach.},
      keywords     = {Computer Vision and Pattern Recognition (cs.CV) (Other) /
                      Artificial Intelligence (cs.AI) (Other) / FOS: Computer and
                      information sciences (Other)},
      cin          = {PGI-15},
      cid          = {I:(DE-Juel1)PGI-15-20210701},
      pnm          = {5234 - Emerging NC Architectures (POF4-523) / GREENEDGE -
                      Taming the environmental impact of mobile networks through
                      GREEN EDGE computing platforms (953775) / BMBF 03ZU1106CA -
                      NeuroSys: Algorithm-Hardware Co-Design (Projekt C) - A
                      (03ZU1106CA) / BMBF 03ZU1106CB - NeuroSys:
                      Algorithm-Hardware Co-Design (Projekt C) - B
                      (BMBF-03ZU1106CB)},
      pid          = {G:(DE-HGF)POF4-5234 / G:(EU-Grant)953775 /
                      G:(BMBF)03ZU1106CA / G:(DE-Juel1)BMBF-03ZU1106CB},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.48550/ARXIV.2403.10173},
      url          = {https://juser.fz-juelich.de/record/1038039},
}