GET: Group Event Transformer for Event-Based Vision

TL;DR

GET introduces a novel transformer backbone for event-based vision that effectively separates temporal-polarity from spatial information, leading to superior performance on classification and detection tasks.

Contribution

The paper proposes a new Group Event Transformer (GET) that decouples temporal-polarity information from spatial features using Group Tokens and dual self-attention, advancing event-based vision models.

Findings

GET outperforms state-of-the-art methods on multiple datasets.

The Group Token representation effectively captures asynchronous event information.

GET demonstrates versatility across classification and detection tasks.

Abstract

Event cameras are a type of novel neuromorphic sen-sor that has been gaining increasing attention. Existing event-based backbones mainly rely on image-based designs to extract spatial information within the image transformed from events, overlooking important event properties like time and polarity. To address this issue, we propose a novel Group-based vision Transformer backbone for Event-based vision, called Group Event Transformer (GET), which de-couples temporal-polarity information from spatial infor-mation throughout the feature extraction process. Specifi-cally, we first propose a new event representation for GET, named Group Token, which groups asynchronous events based on their timestamps and polarities. Then, GET ap-plies the Event Dual Self-Attention block, and Group Token Aggregation module to facilitate effective feature commu-nication and integration in both the spatial and temporal-polarity domains. After that, GET can be integrated with different downstream tasks by connecting it with vari-ous heads. We evaluate our method on four event-based classification datasets (Cifar10-DVS, N-MNIST, N-CARS, and DVS128Gesture) and two event-based object detection datasets (1Mpx and Gen1), and the results demonstrate that GET outperforms other state-of-the-art methods. The code is available at https://github.com/Peterande/GET-Group-Event-Transformer.