Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Silva, Diego A., Elsheikh, Ahmed, Smagulova, Kamilya, Fouda, Mohammed E., Eltawil, Ahmed M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909442023358464
author Silva, Diego A.
Elsheikh, Ahmed
Smagulova, Kamilya
Fouda, Mohammed E.
Eltawil, Ahmed M.
author_facet Silva, Diego A.
Elsheikh, Ahmed
Smagulova, Kamilya
Fouda, Mohammed E.
Eltawil, Ahmed M.
contents Event-based cameras are sensors that simulate the human eye, offering advantages such as high-speed robustness and low power consumption. Established Deep Learning techniques have shown effectiveness in processing event data. Chimera is a Block-Based Neural Architecture Search (NAS) framework specifically designed for Event-Based Object Detection, aiming to create a systematic approach for adapting RGB-domain processing methods to the event domain. The Chimera design space is constructed from various macroblocks, including Attention blocks, Convolutions, State Space Models, and MLP-mixer-based architectures, which provide a valuable trade-off between local and global processing capabilities, as well as varying levels of complexity. The results on the PErson Detection in Robotics (PEDRo) dataset demonstrated performance levels comparable to leading state-of-the-art models, alongside an average parameter reduction of 1.6 times.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19646
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection
Silva, Diego A.
Elsheikh, Ahmed
Smagulova, Kamilya
Fouda, Mohammed E.
Eltawil, Ahmed M.
Computer Vision and Pattern Recognition
Artificial Intelligence
Event-based cameras are sensors that simulate the human eye, offering advantages such as high-speed robustness and low power consumption. Established Deep Learning techniques have shown effectiveness in processing event data. Chimera is a Block-Based Neural Architecture Search (NAS) framework specifically designed for Event-Based Object Detection, aiming to create a systematic approach for adapting RGB-domain processing methods to the event domain. The Chimera design space is constructed from various macroblocks, including Attention blocks, Convolutions, State Space Models, and MLP-mixer-based architectures, which provide a valuable trade-off between local and global processing capabilities, as well as varying levels of complexity. The results on the PErson Detection in Robotics (PEDRo) dataset demonstrated performance levels comparable to leading state-of-the-art models, alongside an average parameter reduction of 1.6 times.
title Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.19646