evMLP: An Efficient Event-Driven MLP Architecture for Vision
This work addresses efficiency challenges in video processing for computer vision applications, presenting an incremental improvement over existing MLP-based methods.
The paper tackles the problem of computational redundancy in processing sequential image data like videos by introducing evMLP, an event-driven MLP architecture that selectively processes patches where changes occur, achieving competitive accuracy on ImageNet and reducing computational cost on video datasets while maintaining output consistency.
Deep neural networks have achieved remarkable results in computer vision tasks. In the early days, Convolutional Neural Networks (CNNs) were the mainstream architecture. In recent years, Vision Transformers (ViTs) have become increasingly popular. In addition, exploring applications of multi-layer perceptrons (MLPs) has provided new perspectives for research into vision model architectures. In this paper, we present evMLP accompanied by a simple event-driven local update mechanism. The proposed evMLP can independently process patches on images or feature maps via MLPs. We define changes between consecutive frames as ``events''. Under the event-driven local update mechanism, evMLP selectively processes patches where events occur. For sequential image data (e.g., video processing), this approach improves computational performance by avoiding redundant computations. Through ImageNet image classification experiments, evMLP attains accuracy competitive with state-of-the-art models. More significantly, experimental results on multiple video datasets demonstrate that evMLP reduces computational cost via its event-driven local update mechanism while maintaining output consistency with its non-event-driven baseline. The code and pre-trained models are available at https://github.com/i-evi/evMLP.