paper-with-me

홈 › Papers

Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation

2023-01-01 · Haeyong Kang, Chang D. Yoo

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.

📄 PDF Abstract BibTeX arXiv:2301.00351

Code (1)

ihaeyong/unbiased-sgg 공식 구현 pytorch

Tasks

Graph GenerationScene Graph GenerationUnbiased Scene Graph Generation

Similar Papers 제목 키워드 기반

Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation

2022-08-15 · Liguang Zhou, Yuhongze Zhou, Tin Lun Lam, Yangsheng Xu

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+3

Gradient Reweighting: Towards Imbalanced Class-Incremental Learning

2024-02-28 · CVPR 2024 1 · Jiangpeng He, Fengqing Zhu

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 Distillation

Effects of sampling skewness of the importance-weighted risk estimator on model selection

2018-04-19 · Wouter M. Kouw, Marco Loog

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 bias

Generalized Unbiased Scene Graph Generation

2023-08-09 · Xinyu Lyu, Lianli Gao, Junlin Xie, Pengpeng Zeng 외

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 Generation

Skew-Probabilistic Neural Networks for Learning from Imbalanced Data

2023-12-10 · Shraddha M. Naik, Tanujit Chakraborty, Madhurima Panja, Abdenour Hadid 외

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…