E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections
This work addresses the need for efficient neural networks in resource-constrained scenarios, though it is incremental as it modifies an existing architecture.
The paper tackles the problem of making ConvNeXt networks lightweight for efficient applications by integrating Cross-Stage Partial Connections and other optimizations, resulting in E-ConvNeXt variants that achieve up to 81.9% Top-1 accuracy on ImageNet with reduced complexity by up to 80%.
Many high-performance networks were not designed with lightweight application scenarios in mind from the outset, which has greatly restricted their scope of application. This paper takes ConvNeXt as the research object and significantly reduces the parameter scale and network complexity of ConvNeXt by integrating the Cross Stage Partial Connections mechanism and a series of optimized designs. The new network is named E-ConvNeXt, which can maintain high accuracy performance under different complexity configurations. The three core innovations of E-ConvNeXt are : (1) integrating the Cross Stage Partial Network (CSPNet) with ConvNeXt and adjusting the network structure, which reduces the model's network complexity by up to 80%; (2) Optimizing the Stem and Block structures to enhance the model's feature expression capability and operational efficiency; (3) Replacing Layer Scale with channel attention. Experimental validation on ImageNet classification demonstrates E-ConvNeXt's superior accuracy-efficiency balance: E-ConvNeXt-mini reaches 78.3% Top-1 accuracy at 0.9GFLOPs. E-ConvNeXt-small reaches 81.9% Top-1 accuracy at 3.1GFLOPs. Transfer learning tests on object detection tasks further confirm its generalization capability.