Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based PerceptionDownload PDF

Published: 01 Feb 2023, Last Modified: 02 Mar 2023ICLR 2023 notable top 25%Readers: Everyone
Keywords: associative memory, memory augmented neural network, spatiotemporal representation, event-based camera, event-based perception, object recognition, attention, set processing
TL;DR: We propose EventFormer, an asynchronous spatiotemporal representation learning framework augmented by an associative memory to efficiently perform event-based perception.
Abstract: We propose $\textit{EventFormer}$, a computationally efficient event-based representation learning framework for asynchronously processing event camera data. EventFormer treats sparse input events as a spatially unordered set and models their spatial interactions using self-attention mechanism. An associative memory-augmented recurrent module is used to correlate with the stored representation computed from past events. A memory addressing mechanism is proposed to store and retrieve the latent states only $\textit{where}$ these events occur and update them only $\textit{when}$ they occur. The representation learning shift from input space to the latent memory space resulting in reduced computation cost for processing each event. We show that EventFormer achieves 0.5$\%$ and 9$\%$ better accuracy with 30000$\times$ and 200$\times$ less computation compared to the state-of-the-art dense and event-based method, respectively, on event-based object recognition datasets.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)
17 Replies