Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Rui, Leng, Luziwei, Che, Kaiwei, Zhang, Hu, Cheng, Jie, Guo, Qinghai, Liao, Jiangxing, Cheng, Ran
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914896470343680
author Zhang, Rui
Leng, Luziwei
Che, Kaiwei
Zhang, Hu
Cheng, Jie
Guo, Qinghai
Liao, Jiangxing
Cheng, Ran
author_facet Zhang, Rui
Leng, Luziwei
Che, Kaiwei
Zhang, Hu
Cheng, Jie
Guo, Qinghai
Liao, Jiangxing
Cheng, Ran
contents Spiking neural networks (SNNs), known for their low-power, event-driven computation and intrinsic temporal dynamics, are emerging as promising solutions for processing dynamic, asynchronous signals from event-based sensors. Despite their potential, SNNs face challenges in training and architectural design, resulting in limited performance in challenging event-based dense prediction tasks compared to artificial neural networks (ANNs). In this work, we develop an efficient spiking encoder-decoder network (SpikingEDN) for large-scale event-based semantic segmentation tasks. To enhance the learning efficiency from dynamic event streams, we harness the adaptive threshold which improves network accuracy, sparsity and robustness in streaming inference. Moreover, we develop a dual-path Spiking Spatially-Adaptive Modulation module, which is specifically tailored to enhance the representation of sparse events and multi-modal inputs, thereby considerably improving network performance. Our SpikingEDN attains a mean intersection over union (MIoU) of 72.57\% on the DDD17 dataset and 58.32\% on the larger DSEC-Semantic dataset, showing competitive results to the state-of-the-art ANNs while requiring substantially fewer computational resources. Our results shed light on the untapped potential of SNNs in event-based vision applications. The source code will be made publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2304_11857
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network
Zhang, Rui
Leng, Luziwei
Che, Kaiwei
Zhang, Hu
Cheng, Jie
Guo, Qinghai
Liao, Jiangxing
Cheng, Ran
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
Spiking neural networks (SNNs), known for their low-power, event-driven computation and intrinsic temporal dynamics, are emerging as promising solutions for processing dynamic, asynchronous signals from event-based sensors. Despite their potential, SNNs face challenges in training and architectural design, resulting in limited performance in challenging event-based dense prediction tasks compared to artificial neural networks (ANNs). In this work, we develop an efficient spiking encoder-decoder network (SpikingEDN) for large-scale event-based semantic segmentation tasks. To enhance the learning efficiency from dynamic event streams, we harness the adaptive threshold which improves network accuracy, sparsity and robustness in streaming inference. Moreover, we develop a dual-path Spiking Spatially-Adaptive Modulation module, which is specifically tailored to enhance the representation of sparse events and multi-modal inputs, thereby considerably improving network performance. Our SpikingEDN attains a mean intersection over union (MIoU) of 72.57\% on the DDD17 dataset and 58.32\% on the larger DSEC-Semantic dataset, showing competitive results to the state-of-the-art ANNs while requiring substantially fewer computational resources. Our results shed light on the untapped potential of SNNs in event-based vision applications. The source code will be made publicly available.
title Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network
topic Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
url https://arxiv.org/abs/2304.11857