KAUST DepartmentElectrical Engineering Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Preprint Posting Date2018-03-31
Online Publication Date2018-12-18
Print Publication Date2018-06
Permanent link to this recordhttp://hdl.handle.net/10754/627545
MetadataShow full item record
AbstractIn 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.
CitationWu, B., Chen, W., Sun, P., Liu, W., Ghanem, B., & Lyu, S. (2018). Tagging Like Humans: Diverse and Distinct Image Annotation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. doi:10.1109/cvpr.2018.00831
SponsorsThis work is supported by Tencent AI Lab. The participation of Bernard Ghanem is supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research. The participation of Siwei Lyu is partially supported by National Science Foundation National Robotics Initiative (NRI) Grant (IIS-1537257) and National Science Foundation of China Project Number 61771341.
PublisherIEEE Computer Societyhelp@computer.org
Conference/Event name31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018