Litcius/Paper detail

ACENet: Auxiliary Context-Information Enhancement Network for RGB-D Indoor Scene Semantic Segmentation

Wujie Zhou, Gao Xu, Fangfang Qiang, Lu Yu

2023IEEE Transactions on Emerging Topics in Computational Intelligence15 citationsDOI

Abstract

Although networks with traditional convolutional neural network (CNN) backbones have achieved remarkable results in red-green-blue–depth (RGB-D) semantic segmentation, convolution cannot easily capture remote dependencies. Transformers encounter no such difficulties and can obtain richer global information. Therefore, we design an auxiliary context-information enhancement network (ACENet) using Swin Transformer as an auxiliary branch to assist the CNN backbone network. First, we input the outputs of each stage of Swin Transformer and ResNet-34 into a module that integrates local and global information and strengthens segmentation through multi-scale fusion and external attention. Then, we add spatial-depth information to the RGB image through a multi-modal fusion module to obtain a high-quality segmented image. Comprehensive experiments show that the proposed ACENet achieves state-of-the-art performance on two common indoor-scene RGB-D semantic-segmentation datasets.

Topics & Concepts

Computer scienceRGB color modelArtificial intelligenceSegmentationTransformerConvolutional neural networkComputer visionPattern recognition (psychology)EngineeringElectrical engineeringVoltageAdvanced Neural Network ApplicationsImage Enhancement TechniquesVideo Surveillance and Tracking Methods