Tagging Like Humans: Diverse and Distinct Image Annotation

Baoyuan Wu, Weidong Chen, Peng Sun, Wei Liu, Bernard Ghanem, Siwei Lyu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Scopus citations

Abstract

In this work we propose a new automatic image annotation model, dubbed diverse and distinct image annotation (D2IA). The generative model D2IA is inspired by the ensemble of human annotations, which create semantically relevant, yet distinct and diverse tags. In D2IA, we generate a relevant and distinct tag subset, in which the tags are relevant to the image contents and semantically distinct to each other, using sequential sampling from a determinantal point process (DPP) model. Multiple such tag subsets that cover diverse semantic aspects or diverse semantic levels of the image contents are generated by randomly perturbing the DPP sampling process. We leverage a generative adversarial network (GAN) model to train D2IA. Extensive experiments including quantitative and qualitative comparisons, as well as human subject studies, on two benchmark datasets demonstrate that the proposed model can produce more diverse and distinct tags than the state-of-the-arts.
Original languageEnglish (US)
Title of host publication2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Societyhelp@computer.org
Pages7967-7975
Number of pages9
ISBN (Print)9781538664209
DOIs
StatePublished - Dec 18 2018

Fingerprint Dive into the research topics of 'Tagging Like Humans: Diverse and Distinct Image Annotation'. Together they form a unique fingerprint.

Cite this