Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification

TL;DR

This paper introduces a dual-stream Transformer and GNN-based framework for event image and voxel data fusion, significantly improving event-based object classification accuracy.

Contribution

It proposes a novel dual-stream architecture with a bottleneck Transformer for effective fusion of event images and voxels, enhancing feature representation.

Findings

Achieves state-of-the-art results on event classification datasets

Effectively models spatial and 3D stereo information separately

Demonstrates superior performance over existing methods

Abstract

Recognizing target objects using an event-based camera draws more and more attention in recent years. Existing works usually represent the event streams into point-cloud, voxel, image, etc, and learn the feature representations using various deep neural networks. Their final results may be limited by the following factors: monotonous modal expressions and the design of the network structure. To address the aforementioned challenges, this paper proposes a novel dual-stream framework for event representation, extraction, and fusion. This framework simultaneously models two common representations: event images and event voxels. By utilizing Transformer and Structured Graph Neural Network (GNN) architectures, spatial information and three-dimensional stereo information can be learned separately. Additionally, a bottleneck Transformer is introduced to facilitate the fusion of the dual-stream information. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance on two widely used event-based classification datasets. The source code of this work is available at: \url{https://github.com/Event-AHU/EFV_event_classification}