ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. Machine Learning and Artificial Intelligence
Volume 8 - 2025 | doi: 10.3389/frai.2025.1644889
This article is part of the Research TopicNeuromorphic Engineering and Brain-Inspired Control for Autonomous Robotics: Bridging Neuroscience and AI for Real-World ApplicationsView all articles
Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection
Provisionally accepted
- 1King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
- 2Cairo University Faculty of Engineering, Cairo, Egypt
- 3University of California, Irvine, Irvine, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Event-based cameras are sensors inspired by the human eye, offering advantages such as highspeed robustness and low power consumption. Established deep learning techniques have proven effective in processing event data, but there remains a significant space of possibilities that could be further explored to maximize the potential of such combinations. In this context, Chimera is a Block-Based Neural Architecture Search (NAS) framework specifically designed for Event-Based Object Detection, aiming to systematically adapt 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, providing a valuable trade-off between local and global processing capabilities, as well as varying levels of complexity. Results on Prophesee's GEN1 dataset demonstrated state-of-the-art mean Average Precision (mAP) while reducing the number of parameters by 1.6x and achieving a 2.1x speed-up.
Keywords: neural architecture search (NAS), Spiking Datasets, Object detecion, zero-shot NAS, Block architecture search
Received: 11 Jun 2025; Accepted: 18 Aug 2025.
Copyright: © 2025 Silva, Elsheikh, Smagulova, Fouda and Eltawil. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Mohammed Fouda, University of California, Irvine, Irvine, United States
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.