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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 30 papers

TitleStatusHype
Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph GenerationCode1
Unbiased Scene Graph Generation in VideosCode1
Vision Relation Transformer for Unbiased Scene Graph GenerationCode1
Head-Tail Cooperative Learning Network for Unbiased Scene Graph GenerationCode0
Skew Class-balanced Re-weighting for Unbiased Scene Graph GenerationCode0
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph GenerationCode0
PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation—0
Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation—0
Unbiased Scene Graph Generation via Two-stage Causal Modeling—0
Rethinking the Evaluation of Unbiased Scene Graph Generation—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.