Context-aware Sparse Spatiotemporal Learning for Event-based Vision

Conference Paper (2025)
Author(s)

Shenqi Wang (TU Delft - Aerospace Engineering)

Guangzhi Tang (Maastricht University)

Research Group
Control & Simulation
DOI related publication
https://doi.org/10.1109/IROS60139.2025.11246424 Final published version
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Control & Simulation
Pages (from-to)
13713-13719
Publisher
IEEE
ISBN (electronic)
9798331543938
Event
2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2025 (2025-10-19 - 2025-10-25), Hangzhou, China
Downloads counter
13
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Event-based camera has emerged as a promising paradigm for robot perception, offering advantages with high temporal resolution, high dynamic range, and robustness to motion blur. However, existing deep learning-based event processing methods often fail to fully leverage the sparse nature of event data, complicating their integration into resource-constrained edge applications. While neuromorphic computing provides an energy-efficient alternative, spiking neural networks struggle to match of performance of state-of-the-art models in complex event-based vision tasks, like object detection and optical flow. Moreover, achieving high activation sparsity in neural networks is still difficult and often demands careful manual tuning of sparsity-inducing loss terms. Here, we propose Context-aware Sparse Spatiotemporal Learning (CSSL), a novel framework that introduces context-aware thresholding to dynamically regulate neuron activations based on the input distribution, naturally reducing activation density without explicit sparsity constraints. Applied to event-based object detection and optical flow estimation, CSSL achieves comparable or superior performance to state-of-the-art methods while maintaining extremely high neuronal sparsity. Our experimental results highlight CSSL's crucial role in enabling efficient event-based vision for neuromorphic processing.

Files

Context-aware_Sparse_Spatiotem... (pdf)
(pdf | 3 Mb)
- Embargo expired in 18-05-2026
Taverne