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
Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph GenerationCode1
CogTree: Cognition Tree Loss for Unbiased Scene Graph GenerationCode1
PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph GenerationCode1
Unbiased Scene Graph Generation from Biased TrainingCode2
Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.