Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation

TL;DR

This paper introduces a lightweight, efficient RGB-D semantic segmentation network that effectively leverages cross-modal features and high-level context, achieving a superior balance of accuracy and computational efficiency.

Contribution

It proposes a novel spatial-information guided adaptive network with a globally guided local affinity context module for improved segmentation robustness and efficiency.

Findings

Outperforms state-of-the-art methods on NYUv2, SUN RGB-D, and Cityscapes datasets.

Achieves better trade-off among accuracy, inference time, and parameters.

Reduces computational complexity while maintaining high segmentation quality.

Abstract

Efficient RGB-D semantic segmentation has received considerable attention in mobile robots, which plays a vital role in analyzing and recognizing environmental information. According to previous studies, depth information can provide corresponding geometric relationships for objects and scenes, but actual depth data usually exist as noise. To avoid unfavorable effects on segmentation accuracy and computation, it is necessary to design an efficient framework to leverage cross-modal correlations and complementary cues. In this paper, we propose an efficient lightweight encoder-decoder network that reduces the computational parameters and guarantees the robustness of the algorithm. Working with channel and spatial fusion attention modules, our network effectively captures multi-level RGB-D features. A globally guided local affinity context module is proposed to obtain sufficient high-level context information. The decoder utilizes a lightweight residual unit that combines short- and long-distance information with a few redundant computations. Experimental results on NYUv2, SUN RGB-D, and Cityscapes datasets show that our method achieves a better trade-off among segmentation accuracy, inference time, and parameters than the state-of-the-art methods. The source code will be at https://github.com/MVME-HBUT/SGACNet