DBiased-P: Dual-Biased Predicate Predictor for unbiased Scene Graph Generation

Xianjing Han, Xuemeng Song, Xingning Dong, Yinwei Wei, Meng Liu, Liqiang Nie

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Abstract

Scene Graph Generation (SGG) is to abstract the objects and their semantic relationships within a given image. Current SGG performance is mainly limited by the biased predicate prediction caused by the long-tailed data distribution. Though many unbiased SGG methods have emerged to enhance the prediction of the tail predicates, their improvements on the tail predicates are often accompanied by the deterioration on the head ones, leading the prediction overly debiased. Toward this end, in this work, we propose a Dual-Biased Predicate Predictor (DBiased-P) to boost the unbiased SGG, which comprises a reweighted primary classifier and an unweighted auxiliary classifier. The former classifier is tail-biased and used for the final predicate prediction, while the latter one is head-biased and designed to boost the head predicate prediction of the primary classifier by a head-oriented soft regularization. Experiments conducted on Visual Genome and Open Image datasets indicate the superiority of our DBiased-P in unbiased SGG, which significantly improves the recall@50 of the state-of-the-art unbiased SGG method DT2- ACBS from 23.3% to 55.5% as well as the mean recall@50 from 35.9% to 37.7%.

Original languageEnglish
Pages (from-to)5319-5329
Number of pages11
JournalIEEE Transactions on Multimedia
Volume25
DOIs
Publication statusPublished - 13 Jul 2022
Externally publishedYes

Keywords

  • KL-Divergence
  • Re-Weighting Classification
  • Scene Graph Generation
  • Vision and Language

Cite this