ICFRNet: Image Complexity Prior Guided Feature Refinement for Real-time Semantic Segmentation

TL;DR

ICFRNet introduces an image complexity prior to guide feature refinement, significantly improving real-time semantic segmentation accuracy while maintaining efficiency on datasets like Cityscapes and CamViD.

Contribution

The paper proposes a novel image complexity prior-guided network that refines segmentation features using an attention mechanism, enhancing real-time segmentation performance.

Findings

Achieves higher accuracy on Cityscapes and CamViD datasets.

Maintains competitive efficiency for real-time applications.

Effectively leverages image complexity as a guiding prior.

Abstract

In this paper, we leverage image complexity as a prior for refining segmentation features to achieve accurate real-time semantic segmentation. The design philosophy is based on the observation that different pixel regions within an image exhibit varying levels of complexity, with higher complexities posing a greater challenge for accurate segmentation. We thus introduce image complexity as prior guidance and propose the Image Complexity prior-guided Feature Refinement Network (ICFRNet). This network aggregates both complexity and segmentation features to produce an attention map for refining segmentation features within an Image Complexity Guided Attention (ICGA) module. We optimize the network in terms of both segmentation and image complexity prediction tasks with a combined loss function. Experimental results on the Cityscapes and CamViD datasets have shown that our ICFRNet achieves higher accuracy with a competitive efficiency for real-time segmentation.