HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation

被引:3
|
作者
Zhou, Zijian [1 ]
Shi, Miaojing [2 ]
Caesar, Holger [3 ]
机构
[1] Kings Coll London, Dept Informat, London, England
[2] Tongji Univ, Coll Elect & Informat Engn, Shanghai, Peoples R China
[3] Delft Univ Technol, Intelligent Vehicles Lab, Delft, Netherlands
关键词
D O I
10.1109/ICCV51070.2023.01978
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to build a scene graph. This task is particularly challenging for two reasons. First, it suffers from a long-tail problem in its relation categories, making naive biased methods more inclined to high-frequency relations. Existing unbiased methods tackle the long-tail problem by data/loss rebalancing to favor low-frequency relations. Second, a subject-object pair can have two or more semantically overlapping relations. While existing methods favor one over the other, our proposed HiLo framework lets different network branches specialize on low and high frequency relations, enforce their consistency and fuse the results. To the best of our knowledge we are the first to propose an explicitly unbiased PSG method. In extensive experiments we show that our HiLo framework achieves state-of-the-art results on the PSG task. We also apply our method to the Scene Graph Generation task that predicts boxes instead of masks and see improvements over all baseline methods. Code is available at https://github.com/franciszzj/HiLo.
引用
收藏
页码:21580 / 21591
页数:12
相关论文
共 50 条
  • [31] Relation-Specific Feature Augmentation for unbiased scene graph generation
    Liu, Zhihong
    Wang, Jianji
    Chen, Hui
    Ma, Yongqiang
    Zheng, Nanning
    PATTERN RECOGNITION, 2025, 157
  • [32] Semantic-enhanced panoptic scene graph generation through hybrid and axial attentions
    Kuang, Xinhe
    Che, Yuxin
    Han, Huiyan
    Liu, Yimin
    COMPLEX & INTELLIGENT SYSTEMS, 2025, 11 (01)
  • [33] Focusing on Flexible Masks: A Novel Framework for Panoptic Scene Graph Generation with Relation Constraints
    Yang, Jiarui
    Wang, Chuan
    Liu, Zeming
    Wu, Jiahong
    Wang, Dongsheng
    Yang, Liang
    Cao, Xiaochun
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 4209 - 4218
  • [34] OpenPSG: Open-Set Panoptic Scene Graph Generation via Large Multimodal Models
    Zhou, Zijian
    Zhu, Zheng
    Caesar, Holger
    Shi, Miaojing
    COMPUTER VISION - ECCV 2024, PT X, 2025, 15068 : 199 - 215
  • [35] Resistance Training Using Prior Bias: Toward Unbiased Scene Graph Generation
    Chen, Chao
    Zhan, Yibing
    Yu, Baosheng
    Liu, Liu
    Luo, Yong
    Du, Bo
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 212 - 220
  • [36] Unbiased Scene Graph Generation via Two-Stage Causal Modeling
    Sun, Shuzhou
    Zhi, Shuaifeng
    Liao, Qing
    Heikkila, Janne
    Liu, Li
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (10) : 12562 - 12580
  • [37] Dual-Branch Hybrid Learning Network for Unbiased Scene Graph Generation
    Zheng, Chaofan
    Gao, Lianli
    Lyu, Xinyu
    Zeng, Pengpeng
    El Saddik, Abdulmotaleb
    Shen, Heng Tao
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (03) : 1743 - 1756
  • [38] Attention redirection transformer with semantic oriented learning for unbiased scene graph generation
    Zhang, Ruonan
    An, Gaoyun
    Cen, Yigang
    Ruan, Qiuqi
    PATTERN RECOGNITION, 2025, 158
  • [39] PPDL: Predicate Probability Distribution based Loss for Unbiased Scene Graph Generation
    Li, Wei
    Zhang, Haiwei
    Bai, Qijie
    Zhao, Guoqing
    Jiang, Ning
    Yuan, Xiaojie
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 19425 - 19434
  • [40] Bridging Visual and Textual Semantics: Towards Consistency for Unbiased Scene Graph Generation
    Zhang, Ruonan
    An, Gaoyun
    Hao, Yiqing
    Wu, Dapeng Oliver
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (11) : 7102 - 7119