MFPNet: Multi-scale Feature Propagation Network For Lightweight Semantic Segmentation
This work addresses the slower progress in lightweight semantic segmentation, which is crucial for resource-constrained applications, but it appears incremental as it builds on existing compact methods.
The paper tackles the problem of limited feature representation in lightweight semantic segmentation by proposing MFPNet, a novel architecture using symmetrical residual blocks and Graph Convolutional Networks for multi-scale feature propagation, achieving superior results on benchmark datasets.
In contrast to the abundant research focusing on large-scale models, the progress in lightweight semantic segmentation appears to be advancing at a comparatively slower pace. However, existing compact methods often suffer from limited feature representation capability due to the shallowness of their networks. In this paper, we propose a novel lightweight segmentation architecture, called Multi-scale Feature Propagation Network (MFPNet), to address the dilemma. Specifically, we design a robust Encoder-Decoder structure featuring symmetrical residual blocks that consist of flexible bottleneck residual modules (BRMs) to explore deep and rich muti-scale semantic context. Furthermore, taking benefit from their capacity to model latent long-range contextual relationships, we leverage Graph Convolutional Networks (GCNs) to facilitate multi-scale feature propagation between the BRM blocks. When evaluated on benchmark datasets, our proposed approach shows superior segmentation results.