DRBANET: A Lightweight Dual-Resolution Network for Semantic Segmentation with Boundary Auxiliary
This work addresses semantic segmentation for applications like autonomous driving by improving boundary handling in a lightweight model, though it is incremental as it builds on existing dual-resolution approaches.
The authors tackled semantic segmentation by proposing DRBANet, a lightweight dual-resolution network that incorporates boundary information to refine results, achieving a promising trade-off between accuracy and efficiency on Cityscapes and CamVid datasets.
Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years. However, most of them ignore the benefit of boundary information. This paper introduces a lightweight dual-resolution network, called DRBANet, aiming to refine semantic segmentation results with the aid of boundary information. DRBANet adopts dual parallel architecture, including: high resolution branch (HRB) and low resolution branch (LRB). Specifically, HRB mainly consists of a set of Efficient Inverted Bottleneck Modules (EIBMs), which learn feature representations with larger receptive fields. LRB is composed of a series of EIBMs and an Extremely Lightweight Pyramid Pooling Module (ELPPM), where ELPPM is utilized to capture multi-scale context through hierarchical residual connections. Finally, a boundary supervision head is designed to capture object boundaries in HRB. Extensive experiments on Cityscapes and CamVid datasets demonstrate that our method achieves promising trade-off between segmentation accuracy and running efficiency.