ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data

• Published in: arXiv.org 2024-07
• Main Authors: Martin-Turrero, Carmen, Bouvier, Maxence, Breitenstein, Manuel, Zanuttigh, Pietro, Parret, Vincent
• Format: Article
• Language: English
• Subjects: Embedding; Gesture recognition; Machine learning; Object recognition; Sampling; Spatiotemporal data; Synchronous machines
• ISSN: 2331-8422

We seek to enable classic processing of continuous ultra-sparse spatiotemporal data generated by event-based sensors with dense machine learning models. We propose a novel hybrid pipeline composed of asynchronous sensing and synchronous processing that combines several ideas: (1) an embedding based on PointNet models -- the ALERT module -- that can continuously integrate new and dismiss old events thanks to a leakage mechanism, (2) a flexible readout of the embedded data that allows to feed any downstream model with always up-to-date features at any sampling rate, (3) exploiting the input sparsity in a patch-based approach inspired by Vision Transformer to optimize the efficiency of the method. These embeddings are then processed by a transformer model trained for object and gesture recognition. Using this approach, we achieve performances at the state-of-the-art with a lower latency than competitors. We also demonstrate that our asynchronous model can operate at any desired sampling rate.