EfficientSegNet: Lightweight Semantic Segmentation with Multi-Scale Feature Fusion and Boundary Enhancement

TL;DR

EfficientSegNet is a lightweight neural network for semantic segmentation that improves accuracy and efficiency for use in devices with limited resources.

Contribution

The novel CADF and DWF modules enable efficient multi-scale feature fusion and boundary enhancement in a lightweight architecture.

Findings

EfficientSegNet achieves high segmentation accuracy while maintaining low computational costs.

The proposed modules effectively recover local details and preserve object boundaries.

The model performs well on public datasets, suitable for real-time applications on resource-constrained devices.

Abstract

Semantic segmentation is a crucial task in computer vision with broad applications in autonomous driving, intelligent surveillance, drone vision, and other fields. The current high-precision segmentation models generally suffer from large parameter sizes, high computational complexity, and substantial memory consumption, which limits their efficient deployment in embedded systems and resource-constrained environments. In addition, traditional methods exhibit significant limitations in handling multi-scale targets and object boundaries, particularly during deep feature extraction, where the loss of shallow spatial information often results in blurred boundaries and reduced segmentation accuracy. To address these challenges, we propose EfficientSegNet, a lightweight and efficient semantic segmentation network. This network features an innovative architecture that integrates the Cascade-Attention Dense Field (CADF) module and the Dynamic Weighting Feature Fusion (DWF) module, effectively reducing computational resource requirements while balancing global semantic information and local detail recovery. Experimental results demonstrate that EfficientSegNet achieves an excellent balance between segmentation accuracy and computational efficiency on multiple public datasets, providing robust support for real-time segmentation tasks and applications on resource-constrained devices.

Figures