# Data-efficient Event Camera Pre-training via Disentangled Masked Modeling

arXiv: https://arxiv.org/abs/2403.00416 · HTML: https://mlsanity.com/paper/2403.00416/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 45 references that are in the map.
- First posted on arXiv 1 Mar 2024.

## Builds on (most cited first, 30 of 35)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy](https://mlsanity.com/paper/2009.08283/) (2020)
- [AEGNN: Asynchronous Event-based Graph Neural Networks](https://mlsanity.com/paper/2203.17149/) (2022)
- [Temporal-wise Attention Spiking Neural Networks for Event Streams Classification](https://mlsanity.com/paper/2107.11711/) (2021)
- [Event-based Asynchronous Sparse Convolutional Networks](https://mlsanity.com/paper/2003.09148/) (2020)
- [Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks](https://mlsanity.com/paper/2106.01862/) (2021)
- [EV-SegNet: Semantic Segmentation for Event-based Cameras](https://mlsanity.com/paper/1811.12039/) (2018)
- [N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras](https://mlsanity.com/paper/2112.01041/) (2021)
- [DDD17: End-To-End DAVIS Driving Dataset](https://mlsanity.com/paper/1711.01458/) (2017)
- [ESS: Learning Event-based Semantic Segmentation from Still Images](https://mlsanity.com/paper/2203.10016/) (2022)
- [GET: Group Event Transformer for Event-Based Vision](https://mlsanity.com/paper/2310.02642/) (2023)
- [Event Enhanced High-Quality Image Recovery](https://mlsanity.com/paper/2007.08336/) (2020)
- [Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras](https://mlsanity.com/paper/1805.07931/) (2018)
- [GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds](https://mlsanity.com/paper/2212.03010/) (2022)
- [LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing](https://mlsanity.com/paper/2011.06176/) (2020)
- [Graph-based Asynchronous Event Processing for Rapid Object Recognition](https://mlsanity.com/paper/2308.14419/) (2023)

## Built on by (most cited first, 9 of 9)

- [EZSR: Event-based Zero-Shot Recognition](https://mlsanity.com/paper/2407.21616/) (2024)
- [CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework](https://mlsanity.com/paper/2504.12576/) (2025)
- [TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras](https://mlsanity.com/paper/2508.00913/) (2025)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [EventFlash: Towards Efficient MLLMs for Event-Based Vision](https://mlsanity.com/paper/2602.03230/) (2026)
- [Revealing Latent Information: A Physics-inspired Self-supervised Pre-training Framework for Noisy and Sparse Events](https://mlsanity.com/paper/2508.05507/) (2025)
- [Scaling Dense Event-Stream Pretraining from Visual Foundation Models](https://mlsanity.com/paper/2603.03969/) (2026)
- [EvtSlowTV -- A Large and Diverse Dataset for Event-Based Depth Estimation](https://mlsanity.com/paper/2511.02953/) (2025)
- [Event-based Action Recognition by Pre-Training on Multi-Frame Representations](https://mlsanity.com/paper/2610.13856/) (2026)

## Abstract (arXiv)

In this paper, we present a new data-efficient voxel-based self-supervised learning method for event cameras. Our pre-training overcomes the limitations of previous methods, which either sacrifice temporal information by converting event sequences into 2D images for utilizing pre-trained image models or directly employ paired image data for knowledge distillation to enhance the learning of event streams. In order to make our pre-training data-efficient, we first design a semantic-uniform masking method to address the learning imbalance caused by the varying reconstruction difficulties of different regions in non-uniform data when using random masking. In addition, we ease the traditional hybrid masked modeling process by explicitly decomposing it into two branches, namely local spatio-temporal reconstruction and global semantic reconstruction to encourage the encoder to capture local correlations and global semantics, respectively. This decomposition allows our selfsupervised learning method to converge faster with minimal pre-training data. Compared to previous approaches, our self-supervised learning method does not rely on paired RGB images, yet enables simultaneous exploration of spatial and temporal cues in multiple scales. It exhibits excellent generalization performance and demonstrates significant improvements across various tasks with fewer parameters and lower computational costs.