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

Zijian Zhou, Miaojing Shi*, Holger Caesar

*Corresponding author for this work

Research output: Contribution to journalConference paperpeer-review

9 Downloads (Pure)


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.
Original languageEnglish
Pages (from-to)21580-21591
Number of pages12
Journal2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Publication statusPublished - 15 Jan 2024
Event2023 IEEE/CVF International Conference on Computer Vision (ICCV) - Paris, France
Duration: 1 Oct 20236 Oct 2023


Dive into the research topics of 'HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation'. Together they form a unique fingerprint.

Cite this