Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-7

Unbiased Scene Graph Generation

3260 papers • 126 benchmarks • 313 datasets

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")

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in unbiased-scene-graph-generation-7

Trend

Dataset

Best Model

Actions

Visual Genome

Visual Genome

Libraries

i

Use these libraries to find unbiased-scene-graph-generation-7 models and implementations

Datasets

Visual Genome

Subtasks

No subtasks available.

Most implemented papers

Unbiased Scene Graph Generation From Biased Training

Yulei Niu, Kaihua Tang, Jianqiang Huang, Jiaxin Shi, Hanwang Zhang•Wed Feb 26 2020

A novel SGG framework based on causal inference but not the conventional likelihood is presented, which uses Total Direct Effect (TDE) as the proposed final predicate score for unbiased SGG and can be widely applied in the community who seeks unbiased predictions.

787

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation

Songyang Zhang, Rongjie Li, Bo Wan, Xuming He•Wed Mar 31 2021

This work introduces a novel confidence-aware bipartite graph neural network with adaptive message propagation mechanism for unbiased scene graph generation and proposes an efficient bi-level data resampling strategy to alleviate the imbalanced data distribution problem in training the authors' graph network.

249 0

Fine-Grained Scene Graph Generation with Data Transfer

Tat-seng Chua, Maosong Sun, Zhiyuan Liu, Yuan Yao, Ao Zhang, Qi'an Chen, Wei Ji•Mon Mar 21 2022

This work proposes a novel Internal and External Data Transfer (IETrans) method, which can be applied in a plug-and-play fashion and expanded to large SGG with 1,807 predicate classes, which tries to relieve the data distribution problem by automatically creating an enhanced dataset that provides more sufficient and coherent annotations for all predicates.

112 0

PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation

Xiansheng Hua, Shaotian Yan, Chen Shen, Zhongming Jin, Jianqiang Huang, Rongxin Jiang, Yao-wu Chen•Tue Sep 01 2020

A novel Predicate-Correlation Perception Learning scheme to adaptively seek out appropriate loss weights by directly perceiving and utilizing the correlation among predicate classes is proposed, which significantly outperforms previous state-of-the-art methods.

142 0

CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation

Qi Wu, J. Yu, Yuan Chai, Yue Hu•Tue Sep 15 2020

This work builds a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model, and proposes a debiasing loss specially for this cognitive structure, which supports coarse-to-fine distinction for the correct relationships.

125 0

Recovering the Unbiased Scene Graphs from the Biased Ones

Jiashi Feng, Roger Zimmermann, Meng-Jiun Chiou, Henghui Ding, Hanshu Yan, Changhu Wang•Sun Jul 04 2021

This paper shows that, due to the missing labels, SGG can be viewed as a "Learning from Positive and Unlabeled data" (PU learning) problem, where the reporting bias can be removed by recovering the unbiased probabilities from the biased ones by utilizing label frequencies.

128 0

Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation

Baosheng Yu, Chao Chen, Yibing Zhan, Liu Liu, Yong Luo, Bo Du•Mon Jan 17 2022

Resistance Training using Prior Bias (RTPB) uses a distributed-based prior bias to improve models' detecting ability on less frequent relationships during training, thus improving the model generalizability on tail categories.

51 0

Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation

Tian Gan, Jianlong Wu, Liqiang Nie, Xuemeng Song, Xingning Dong, Yuan-Chia Cheng•Thu Mar 17 2022

A novel Stacked Hybrid-Attention network is presented, which facilitates the intra-modal refinement as well as the intermodal interaction, to serve as the encoder and an innovative Group Collaborative Learning strategy is devised to optimize the decoder.

114 0

Dual-Branch Hybrid Learning Network for Unbiased Scene Graph Generation

Lianli Gao, Hengtao Shen, A. E. Saddik, Chao Zheng, Xinyu Lyu, Pengpeng Zeng•Fri Jul 15 2022

A Dual-branch Hybrid Learning network (DHL) to take care of both head predicates and tail ones for SGG, including a Coarse-grained Learning Branch (CLB) and a Fine-grained Learning Branch (FLB).

26 0

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

Haeyong Kang, C. D. Yoo•Sat Dec 31 2022

The Skew Class-Balanced Re-Weighting (SCR) loss function is considered for the unbiased SGG models and is 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.

10 0

Adding a benchmark result helps the community track progress.

Unbiased Scene Graph Generation | State-of-the-Art