Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection [article]

Kaihua Zhang, Tengpeng Li, Shiwen Shen, Bo Liu, Jin Chen, Qingshan Liu
2020 arXiv   pre-print
Co-saliency detection aims to discover the common and salient foregrounds from a group of relevant images. For this task, we present a novel adaptive graph convolutional network with attention graph clustering (GCAGC). Three major contributions have been made, and are experimentally shown to have substantial practical merits. First, we propose a graph convolutional network design to extract information cues to characterize the intra- and interimage correspondence. Second, we develop an
more » ... graph clustering algorithm to discriminate the common objects from all the salient foreground objects in an unsupervised fashion. Third, we present a unified framework with encoder-decoder structure to jointly train and optimize the graph convolutional network, attention graph cluster, and co-saliency detection decoder in an end-to-end manner. We evaluate our proposed GCAGC method on three cosaliency detection benchmark datasets (iCoseg, Cosal2015 and COCO-SEG). Our GCAGC method obtains significant improvements over the state-of-the-arts on most of them.
arXiv:2003.06167v1 fatcat:viapz273g5cv7lzln7x76pfuxq