Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation
An unbiased scene graph generation (SGG) algorithm referred to as Skew Class-balanced Re-weighting (SCR) is proposed for considering the unbiased predicate prediction caused by the long-tailed distribution. The prior works focus mainly on alleviating the deteriorating performances of the minority predicate predictions, showing drastic dropping recall scores, i.e., losing the majority predicate performances. It has not yet correctly analyzed the trade-off between majority and minority predicate performances in the limited SGG datasets. In this paper, to alleviate the issue, the Skew Class-balanced Re-weighting (SCR) loss function is considered for the unbiased SGG models. Leveraged by the skewness of biased predicate predictions, the SCR estimates the target predicate weight coefficient and then re-weights more to the biased predicates for better trading-off between the majority predicates and the minority ones. Extensive experiments conducted on the standard Visual Genome dataset and Open Image V4 \& V6 show the performances and generality of the SCR with the traditional SGG models.
Code (1)
Tasks
Graph GenerationScene Graph GenerationUnbiased Scene Graph GenerationSimilar Papers 제목 키워드 기반
Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation
Scene graph generation (SGG) has gained tremendous progress in recent years. However, its underlying long-tailed distribution of predicate classes is a challenging problem. For extremely unbalanced predicate distribution…
DiversityGraph GenerationMixture-of-Expertsobject-detection+3Gradient Reweighting: Towards Imbalanced Class-Incremental Learning
Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data while retaining learned knowledge. A major challenge of CIL arises when applying to real-world data characteri…
class-incremental learningClass Incremental LearningIncremental LearningKnowledge DistillationEffects of sampling skewness of the importance-weighted risk estimator on model selection
Importance-weighting is a popular and well-researched technique for dealing with sample selection bias and covariate shift. It has desirable characteristics such as unbiasedness, consistency and low computational complex…
Model SelectionSelection biasGeneralized Unbiased Scene Graph Generation
Existing Unbiased Scene Graph Generation (USGG) methods only focus on addressing the predicate-level imbalance that high-frequency classes dominate predictions of rare ones, while overlooking the concept-level imbalance.…
Graph GenerationScene Graph GenerationUnbiased Scene Graph GenerationSkew-Probabilistic Neural Networks for Learning from Imbalanced Data
Real-world datasets often exhibit imbalanced data distribution, where certain class levels are severely underrepresented. In such cases, traditional pattern classifiers have shown a bias towards the majority class, imped…