arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.14178cs.CV
收藏

EvSegSNN:面向事件数据的神经形态语义分割

EvSegSNN: Neuromorphic Semantic Segmentation for Event Data

i3S / CNRS Université Côte d’Azur(蔚蓝海岸大学 i3S / 法国国家科学研究中心)

Dalia Hareb, Jean Martinet

AI总结:

针对传统深度语义分割模型算力与内存消耗高、难以部署在资源受限系统的问题,该研究提出结合SNN与事件相机的EvSegSNN架构,在DDD17数据集上MIoU优于同类SOTA模型,参数量减少1.6倍且无需批量归一化。

摘要:

语义分割是一项重要的计算机视觉任务,尤其适用于自动驾驶车辆与无人机的场景理解和导航。目前已有多种深度神经网络架构被设计用于解决该任务,但这类模型计算成本极高、内存消耗大,并不适合部署在资源受限的系统中。为解决这一局限,我们提出一种端到端的生物启发式语义分割方法,将脉冲神经网络(SNNs,传统神经网络的低功耗替代方案)与事件相机相结合,事件相机的输出数据可直接作为这类神经网络的输入。我们设计了EvSegSNN,这是一种具备生物合理性的编码-解码U型架构,采用参数化泄漏积分发放神经元,旨在实现资源占用与性能之间的权衡。在DDD17数据集上开展的实验表明,EvSegSNN在平均交并比(MIoU)指标上优于最接近的现有最优模型,同时参数量减少了1.6倍,且省去了批量归一化步骤。

英文摘要:

Semantic segmentation is an important computer vision task, particularly for scene understanding and navigation of autonomous vehicles and UAVs. Several variations of deep neural network architectures have been designed to tackle this task. However, due to their huge computational costs and their high memory consumption, these models are not meant to be deployed on resource-constrained systems. To address this limitation, we introduce an end-to-end biologically inspired semantic segmentation approach by combining Spiking Neural Networks (SNNs, a low-power alternative to classical neural networks) with event cameras whose output data can directly feed these neural network inputs. We have designed EvSegSNN, a biologically plausible encoder-decoder U-shaped architecture relying on Parametric Leaky Integrate and Fire neurons in an objective to trade-off resource usage against performance. The experiments conducted on DDD17 demonstrate that EvSegSNN outperforms the closest state-of-the-art model in terms of MIoU while reducing the number of parameters by a factor of $1.6$ and sparing a batch normalization stage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑