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

Understand

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.