Segmenting Objects From Relational Visual Data
Lists
Only you see this
Abstract
In this article, we model a set of pixel-wise object segmentation tasks, i.e., automatic video segmentation (AVS), image co-segmentation (ICS) and few-shot semantic segmentation (FSS), from a unified view of segmenting objects from relational visual data. To this end, an attentive graph neural network (AGNN) is proposed, which tackles these tasks in a holistic fashion. Specifically, AGNN formulates the tasks as a process of iterative information fusion over data graphs. It builds a fully connected graph to efficiently represent visual data as nodes, and relations between data instances as edges. Through parametric message passing, AGNN is able to fully capture knowledge from the relational visual data, enabling more accurate object discovery and segmentation. Experiments show that AGNN can automatically highlight primary foreground objects from video sequences (i.e., AVS), and extract common objects from noisy collections of semantically related images (i.e., ICS). Remarkably, with proper modifications, AGNN can even generalize segmentation ability to new categories with only a few annotated data (i.e., FSS). Taken together, our results demonstrate that AGNN provides a powerful tool that is applicable to a wide range of pixel-wise object pattern understanding tasks, given large-scale, or even a few, relational visual data.
BibTeX
@article{lu2022segmenting,
author = {Xiankai Lu and Wenguan Wang and Jianbing Shen and David J. Crandall and Luc Van Gool},
title = {{Segmenting Objects From Relational Visual Data}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2022},
doi = {10.1109/tpami.2021.3115815},
}Loading related content...