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 1–10 of 30 papers

TitleStatusHype
Unbiased Scene Graph Generation from Biased TrainingCode2
Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph GenerationCode1
Compositional Feature Augmentation for Unbiased Scene Graph GenerationCode1
Recovering the Unbiased Scene Graphs from the Biased OnesCode1
CogTree: Cognition Tree Loss for Unbiased Scene Graph GenerationCode1
Dual-branch Hybrid Learning Network for Unbiased Scene Graph GenerationCode1
PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph GenerationCode1
Fine-Grained Scene Graph Generation with Data TransferCode1
Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph GenerationCode1
Resistance Training using Prior Bias: toward Unbiased Scene Graph GenerationCode1
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.