SOTAVerified

Unbiased Scene Graph Generation

Unbiased Scene Graph Generation (Unbiased SGG) aims to predict more informative scene graphs composed of more "tail predicates" *(in contrast to "head predicates" in terms of class frequencies) by dealing with the skewed, long-tailed predicate class distribution. (Definition from Chiou et al. "Recovering the Unbiased Scene Graphs from the Biased Ones")

Papers

Showing 2630 of 30 papers

TitleStatusHype
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation0
Rethinking the Evaluation of Unbiased Scene Graph Generation0
Learning Structured Representations of Visual Scenes0
PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation0
Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.