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
  • [1] Panoptic Scene Graph Generation
    Yang, Jingkang
    Ang, Yi Zhe
    Guo, Zujin
    Zhou, Kaiyang
    Zhang, Wayne
    Liu, Ziwei
    COMPUTER VISION - ECCV 2022, PT XXVII, 2022, 13687 : 178 - 196
  • [2] Panoptic Video Scene Graph Generation
    Yang, Jingkang
    Peng, Wenxuan
    Li, Xiangtai
    Guo, Zujin
    Chen, Liangyu
    Li, Bo
    Ma, Zheng
    Zhou, Kaiyang
    Zhang, Wayne
    Loy, Chen Change
    Liu, Ziwei
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 18675 - 18685
  • [3] Unbiased Scene Graph Generation in Videos
    Nag, Sayak
    Min, Kyle
    Tripathi, Subama
    Roy-Chowdhury, Amit K.
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 22803 - 22813
  • [4] Relation Detection with Transformers for Panoptic Scene Graph Generation
    Liu, Chang
    Yan, Wenchao
    Chen, Shilin
    Huang, Liqun
    Huang, Xiaotao
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2024, PT IV, 2025, 15034 : 223 - 238
  • [5] 4D Panoptic Scene Graph Generation
    Yang, Jingkang
    Cen, Jun
    Peng, Wenxuan
    Liu, Shuai
    Hong, Fangzhou
    Li, Xiangtai
    Zhou, Kaiyang
    Chen, Qifeng
    Liu, Ziwei
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36, NEURIPS 2023, 2023,
  • [6] TextPSG: Panoptic Scene Graph Generation from Textual Descriptions
    Zhao, Chengyang
    Shen, Yikang
    Chen, Zhenfang
    Ding, Mingyu
    Gan, Chuang
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 2827 - 2838
  • [7] GroupRF: Panoptic Scene Graph Generation with group relation tokens
    Wang, Hongyun
    Li, Jiachen
    Xiang, Xiang
    Xie, Qing
    Ma, Yanchun
    Liu, Yongjian
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2025, 107
  • [8] Panoptic Scene Graph Generation with Semantics-Prototype Learning
    Li, Li
    Ji, Wei
    Wu, Yiming
    Li, Mengze
    Qin, You
    Wei, Lina
    Zimmermann, Roger
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 4, 2024, : 3145 - 3153
  • [9] A Fair Ranking and New Model for Panoptic Scene Graph Generation
    Lorenz, Julian
    Pest, Alexander
    Kienzle, Daniel
    Ludwig, Katja
    Lienhart, Rainer
    COMPUTER VISION - ECCV 2024, PT LXI, 2025, 15119 : 148 - 164
  • [10] Adaptive Feature Learning for Unbiased Scene Graph Generation
    Yang, Jiarui
    Wang, Chuan
    Yang, Liang
    Jiang, Yuchen
    Cao, Angelina
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 2252 - 2265