Scalable Event Cloud Network for Event-based Classification

Event cameras are biologically inspired sensors garnering significant attention from both industry and academia. Mainstream methods favor frame and voxel representations, which reach a satisfactory performance while introducing time-consuming transformations, bulky models, and sacrificing fine-grained temporal information. Alternatively, Point Cloud representation demonstrates promise in addressing the mentioned weaknesses, but it has limited scalability in abstracting features of higher spatial resolution and longer temporal sequence events. In this paper, we propose a Scalable Network named SECNet to leverage Event Cloud representation. SECNet integrates polarity at the structural level by innovating the Event-based Group and Sampling module rather than only at the input level. To accommodate the surge in the number of events, SECNet embraces feature extraction in the frequency domain via the Fourier transform. This approach not only substantially extinguishes the explosion of Multiply Accumulate Operations but also effectively abstracts spatio-temporal features. We conducted extensive experiments on ten event-based datasets, and substantiate the scalability, effectiveness, and efficiency of SECNet. Our code will be available at: https://github.com/rhwxmx/SECNet_ICML.

Event cameras are energy-efficient vision sensors that capture only changes in a scene, allowing them to operate much faster and with lower power consumption than traditional cameras. They are promising for applications such as robotics, autonomous driving, and wearable devices. In this paper, we propose SECNet, a lightweight AI framework designed specifically for event camera data. Unlike many existing methods that first convert events into images, SECNet directly processes the original event stream, preserving detailed temporal information while reducing computational cost. SECNet also introduces an efficient frequency-based feature extraction strategy that improves scalability for large event streams and makes the model more suitable for edge devices. Experiments on ten benchmark datasets show that SECNet achieves strong performance across multiple tasks while remaining fast and hardware-efficient.