# Low-Latency Event-Based Object Detection with Spatially-Sparse Linear Attention

arXiv: https://arxiv.org/abs/2603.06228 · HTML: https://mlsanity.com/paper/2603.06228/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 51 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [Resurrecting Recurrent Neural Networks for Long Sequences](https://mlsanity.com/paper/2303.06349/) (2023)
- [Parallelizing Linear Transformers with the Delta Rule over Sequence Length](https://mlsanity.com/paper/2406.06484/) (2024)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Learning to Detect Objects with a 1 Megapixel Event Camera](https://mlsanity.com/paper/2009.13436/) (2020)
- [AEGNN: Asynchronous Event-based Graph Neural Networks](https://mlsanity.com/paper/2203.17149/) (2022)
- [A Large Scale Event-based Detection Dataset for Automotive](https://mlsanity.com/paper/2001.08499/) (2020)
- [Event-based Asynchronous Sparse Convolutional Networks](https://mlsanity.com/paper/2003.09148/) (2020)
- [State Space Models for Event Cameras](https://mlsanity.com/paper/2402.15584/) (2024)
- [GET: Group Event Transformer for Event-Based Vision](https://mlsanity.com/paper/2310.02642/) (2023)
- [EventNet: Asynchronous Recursive Event Processing](https://mlsanity.com/paper/1812.07045/) (2018)
- [From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection](https://mlsanity.com/paper/2304.13455/) (2023)
- [Graph-based Asynchronous Event Processing for Rapid Object Recognition](https://mlsanity.com/paper/2308.14419/) (2023)
- [MoM: Linear Sequence Modeling with Mixture-of-Memories](https://mlsanity.com/paper/2502.13685/) (2025)
- [Scene Adaptive Sparse Transformer for Event-based Object Detection](https://mlsanity.com/paper/2404.01882/) (2024)
- [Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models](https://mlsanity.com/paper/2404.18508/) (2024)
- [Fully neuromorphic vision and control for autonomous drone flight](https://mlsanity.com/paper/2303.08778/) (2023)
- [SMamba: Sparse Mamba for Event-based Object Detection](https://mlsanity.com/paper/2501.11971/) (2025)

## Built on by (most cited first, 3 of 3)

- [FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detection](https://mlsanity.com/paper/2606.17334/) (2026)
- [Neural Events: Discrete Asynchronous Autoencoders for Event-Based Vision](https://mlsanity.com/paper/2606.19835/) (2026)
- [Bend the Clock: Predicting Ahead to Beat Latency in Event-Based Object Detection](https://mlsanity.com/paper/2609.26919/) (2026)

## Abstract (arXiv)

Event cameras provide sequential visual data with spatial sparsity and high temporal resolution, making them attractive for low-latency object detection. Existing asynchronous event-based neural networks exploit this low-latency advantage by updating predictions event by event, but still suffer from two bottlenecks: recurrent architectures are difficult to train efficiently on long sequences, and improving accuracy often increases per-event computation and latency. Linear attention is appealing because it enables parallel training and recurrent inference. However, its dense state updates make per-event computation scale with the state size, yielding a poor accuracy-efficiency trade-off for object detection, where accurate localization requires fine-grained spatial states. The key challenge is therefore to introduce sparse state activation that exploits the spatial sparsity of events while preserving efficient parallel training. We propose Spatially-Sparse Linear Attention (SSLA), which introduces a mixture-of-spaces state decomposition and a scatter-compute-gather training procedure, enabling state-level sparsity as well as training parallelism. Building on SSLA, we develop an end-to-end asynchronous linear attention model, SSLA-Det, for low-latency event-based object detection. On Gen1 and N-Caltech101, SSLA-Det achieves state-of-the-art accuracy among asynchronous methods, reaching 0.375 mAP and 0.515 mAP, respectively, while reducing per-event computation by over 20 times compared with the strongest prior asynchronous baseline, demonstrating the potential of linear attention for low-latency event-based vision.