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 21–30 of 30 papers

TitleStatusHype
Unbiased Scene Graph Generation using Predicate Similarities—0
ALF: Adaptive Label Finetuning for Scene Graph Generation—0
FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing—0
Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction—0
Generalized Unbiased Scene Graph Generation—0
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation—0
Ensemble Predicate Decoding for Unbiased Scene Graph Generation—0
Skew Class-balanced Re-weighting for Unbiased Scene Graph GenerationCode0
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph GenerationCode0
Head-Tail Cooperative Learning Network for Unbiased Scene Graph GenerationCode0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.