Grounding referring expressions in images by variational context

We focus on grounding (i.e., localizing or linking) referring expressions in images, e.g., 'largest elephant standing behind baby elephant'. This is a general yet challenging vision-language task since it does not only require the localization of objects, but also the multimodal comprehens...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Hanwang, Niu, Yulei, Chang, Shih-Fu
Other Authors: School of Computer Science and Engineering
Format: Conference or Workshop Item
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/143054
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:We focus on grounding (i.e., localizing or linking) referring expressions in images, e.g., 'largest elephant standing behind baby elephant'. This is a general yet challenging vision-language task since it does not only require the localization of objects, but also the multimodal comprehension of context - visual attributes (e.g., 'largest', 'baby') and relationships (e.g., 'behind') that help to distinguish the referent from other objects, especially those of the same category. Due to the exponential complexity involved in modeling the context associated with multiple image regions, existing work oversimplifies this task to pairwise region modeling by multiple instance learning. In this paper, we propose a variational Bayesian method, called Variational Context, to solve the problem of complex context modeling in referring expression grounding. Our model exploits the reciprocal relation between the referent and context, i.e., either of them influences estimation of the posterior distribution of the other, and thereby the search space of context can be greatly reduced. We also extend the model to unsupervised setting where no annotation for the referent is available. Extensive experiments on various benchmarks show consistent improvement over state-of-the-art methods in both supervised and unsupervised settings. The code is available at https://github.com/yuleiniu/vc/.