# Pushing the boundaries of event subsampling in event-based video classification using CNNs

arXiv: https://arxiv.org/abs/2409.08953 · HTML: https://mlsanity.com/paper/2409.08953/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 13 Sep 2024.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification](https://mlsanity.com/paper/1803.07913/) (2018)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018)
- [Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios](https://mlsanity.com/paper/1709.06310/) (2017)
- [Event-based Asynchronous Sparse Convolutional Networks](https://mlsanity.com/paper/2003.09148/) (2020)
- [Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks](https://mlsanity.com/paper/2302.08890/) (2023)
- [Graph-Based Object Classification for Neuromorphic Vision Sensing](https://mlsanity.com/paper/1908.06648/) (2019)
- [EventNet: Asynchronous Recursive Event Processing](https://mlsanity.com/paper/1812.07045/) (2018)
- [HFirst: A Temporal Approach to Object Recognition](https://mlsanity.com/paper/1508.01176/) (2015)
- [Masked Event Modeling: Self-Supervised Pretraining for Event Cameras](https://mlsanity.com/paper/2212.10368/) (2022)
- [Autonomous Drone Racing: A Survey](https://mlsanity.com/paper/2301.01755/) (2023)
- [Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras](https://mlsanity.com/paper/2211.12324/) (2022)
- [Efficient recurrent architectures through activity sparsity and sparse back-propagation through time](https://mlsanity.com/paper/2206.06178/) (2022)
- [Feedback control of event cameras](https://mlsanity.com/paper/2105.00409/) (2021)
- [Are High-Resolution Event Cameras Really Needed?](https://mlsanity.com/paper/2203.14672/) (2022)
- [How Many Events do You Need? Event-based Visual Place Recognition Using Sparse But Varying Pixels](https://mlsanity.com/paper/2206.13673/) (2022)
- [Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event Streams](https://mlsanity.com/paper/2303.03856/) (2023)
- [Spiking Neural Networks for event-based action recognition: A new task to understand their advantage](https://mlsanity.com/paper/2209.14915/) (2022)
- [Event-based Navigation for Autonomous Drone Racing with Sparse Gated Recurrent Network](https://mlsanity.com/paper/2204.02120/) (2022)
- [Synthesis of neural networks for spatio-temporal spike pattern recognition and processing](https://mlsanity.com/paper/1304.7118/) (2013)

## Built on by (most cited first, 2 of 2)

- [Making Every Event Count: Balancing Data Efficiency and Accuracy in Event Camera Subsampling](https://mlsanity.com/paper/2505.21187/) (2025)
- [Probabilistic Online Event Downsampling](https://mlsanity.com/paper/2506.02547/) (2025)

## Abstract (arXiv)

Event cameras offer low-power visual sensing capabilities ideal for edge-device applications. However, their high event rate, driven by high temporal details, can be restrictive in terms of bandwidth and computational resources. In edge AI applications, determining the minimum amount of events for specific tasks can allow reducing the event rate to improve bandwidth, memory, and processing efficiency. In this paper, we study the effect of event subsampling on the accuracy of event data classification using convolutional neural network (CNN) models. Surprisingly, across various datasets, the number of events per video can be reduced by an order of magnitude with little drop in accuracy, revealing the extent to which we can push the boundaries in accuracy vs. event rate trade-off. Additionally, we also find that lower classification accuracy in high subsampling rates is not solely attributable to information loss due to the subsampling of the events, but that the training of CNNs can be challenging in highly subsampled scenarios, where the sensitivity to hyperparameters increases. We quantify training instability across multiple event-based classification datasets using a novel metric for evaluating the hyperparameter sensitivity of CNNs in different subsampling settings. Finally, we analyze the weight gradients of the network to gain insight into this instability.