paper-with-me

홈 › Papers

Ensemble Predicate Decoding for Unbiased Scene Graph Generation

2024-08-26 · Jiasong Feng, LiChun Wang, Hongbo Xu, Kai Xu, BaoCai Yin

Scene Graph Generation (SGG) aims to generate a comprehensive graphical representation that accurately captures the semantic information of a given scenario. However, the SGG model's performance in predicting more fine-grained predicates is hindered by a significant predicate bias. According to existing works, the long-tail distribution of predicates in training data results in the biased scene graph. However, the semantic overlap between predicate categories makes predicate prediction difficult, and there is a significant difference in the sample size of semantically similar predicates, making the predicate prediction more difficult. Therefore, higher requirements are placed on the discriminative ability of the model. In order to address this problem, this paper proposes Ensemble Predicate Decoding (EPD), which employs multiple decoders to attain unbiased scene graph generation. Two auxiliary decoders trained on lower-frequency predicates are used to improve the discriminative ability of the model. Extensive experiments are conducted on the VG, and the experiment results show that EPD enhances the model's representation capability for predicates. In addition, we find that our approach ensures a relatively superior predictive capability for more frequent predicates compared to previous unbiased SGG methods.

📄 PDF Abstract BibTeX arXiv:2408.14187

Code (0)

등록된 구현이 없습니다.

Tasks

Graph GenerationScene Graph GenerationUnbiased Scene Graph Generation

Similar Papers 제목 키워드 기반

Peer Learning for Unbiased Scene Graph Generation

2022-12-31 · Liguang Zhou, Junjie Hu, Yuhongze Zhou, Tin Lun Lam 외

Unbiased scene graph generation (USGG) is a challenging task that requires predicting diverse and heavily imbalanced predicates between objects in an image. To address this, we propose a novel framework peer learning tha…

Graph GenerationScene Graph GenerationUnbiased Scene Graph Generation

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

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 wor…

Graph GenerationScene Graph GenerationUnbiased Scene Graph Generation

Rethinking the Evaluation of Unbiased Scene Graph Generation

2022-08-03 · Xingchen Li, Long Chen, Jian Shao, Shaoning Xiao 외

Current Scene Graph Generation (SGG) methods tend to predict frequent predicate categories and fail to recognize rare ones due to the severe imbalanced distribution of predicates. To improve the robustness of SGG models …

DiversityGraph GenerationScene Graph GenerationTriplet+1

PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation

2022-01-01 · CVPR 2022 1 · Wei Li, Haiwei Zhang, Qijie Bai, Guoqing Zhao 외

Scene Graph Generation (SGG) has attracted more and more attention from visual researchers in recent years, since Scene Graph (SG) is valuable in many downstream tasks due to its rich structural-semantic details. How…

Graph GenerationPredicate ClassificationScene Graph GenerationUnbiased Scene Graph Generation