ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Gesture RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Making Asynchronous Stochastic Gradient Descent Work for Transformers
Asynchronous stochastic gradient descent (SGD) is attractive from a speed perspective because workers do not wait for synchronization. However, the Transformer model converges poorly with asynchronous SGD, resulting in s…
GPUMachine TranslationTranslationAsynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning
Sharpness-Aware Minimization (SAM) is an optimization method that improves generalization performance of machine learning models. Despite its superior generalization, SAM has not been actively used in real-world applicat…
Deep LearningTAPFormer: Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of Frames and Events
Tracking any point (TAP) is a fundamental yet challenging task in computer vision, requiring high precision and long-term motion reasoning. Recent attempts to combine RGB frames and event streams have shown promise, yet …
Point TrackingAsynchronous Heavy-Tailed Optimization
Heavy-tailed stochastic gradient noise, commonly observed in transformer models, can destabilize the optimization process. Recent works mainly focus on developing and understanding approaches to address heavy-tailed nois…
FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers
Federated learning (FL) involves training a model over massive distributed devices, while keeping the training data localized. This form of collaborative learning exposes new tradeoffs among model convergence speed, mode…
Federated Learning