Litcius/Paper detail

Context-Aware Graph Label Propagation Network for Saliency Detection

Wei Ji, Xi Li, Lina Wei, Fei Wu, Yueting Zhuang

2020IEEE Transactions on Image Processing34 citationsDOI

Abstract

Recently, a large number of existing methods for saliency detection have mainly focused on designing complex network architectures to aggregate powerful features from backbone networks. However, contextual information is not well utilized, which often causes false background regions and blurred object boundaries. Motivated by these issues, we propose an easyto-implement module that utilizes the edge-preserving ability of superpixels and the graph neural network to interact the context of superpixel nodes. In more detail, we first extract the features from the backbone network and obtain the superpixel information of images. This step is followed by superpixel pooling in which we transfer the irregular superpixel information to a structured feature representation. To propagate the information among the foreground and background regions, we use a graph neural network and self-attention layer to better evaluate the degree of saliency degree. Additionally, an affinity loss is proposed to regularize the affinity matrix to constrain the propagation path. Moreover, we extend our module to a multiscale structure with different numbers of superpixels. Experiments on five challenging datasets show that our approach can improve the performance of three baseline methods in terms of some popular evaluation metrics.

Topics & Concepts

Computer sciencePoolingArtificial intelligencePattern recognition (psychology)Backbone networkGraphContext (archaeology)Feature (linguistics)Feature extractionRepresentation (politics)Theoretical computer sciencePolitical scienceLawPoliticsPhilosophyBiologyLinguisticsComputer networkPaleontologyVisual Attention and Saliency DetectionOlfactory and Sensory Function StudiesImage and Video Quality Assessment