Pair then Relation: Pair-Net for Panoptic Scene Graph Generation

TL;DR

This paper introduces Pair-Net, a novel framework for Panoptic Scene Graph generation that improves relationship prediction by focusing on pair-wise object relationships, achieving significant performance gains over previous methods.

Contribution

The paper proposes Pair-Net, a new approach that enhances PSG by explicitly modeling pair-wise relationships with a Pair Proposal Network and a lightweight Matrix Learner.

Findings

Over 10% absolute improvement over PSGFormer baseline

Effective modeling of pair-wise relationships enhances PSG performance

Code is publicly available for reproducibility

Abstract

Panoptic Scene Graph (PSG) is a challenging task in Scene Graph Generation (SGG) that aims to create a more comprehensive scene graph representation using panoptic segmentation instead of boxes. Compared to SGG, PSG has several challenging problems: pixel-level segment outputs and full relationship exploration (It also considers thing and stuff relation). Thus, current PSG methods have limited performance, which hinders downstream tasks or applications. The goal of this work aims to design a novel and strong baseline for PSG. To achieve that, we first conduct an in-depth analysis to identify the bottleneck of the current PSG models, finding that inter-object pair-wise recall is a crucial factor that was ignored by previous PSG methods. Based on this and the recent query-based frameworks, we present a novel framework: Pair then Relation (Pair-Net), which uses a Pair Proposal Network (PPN) to learn and filter sparse pair-wise relationships between subjects and objects. Moreover, we also observed the sparse nature of object pairs for both Motivated by this, we design a lightweight Matrix Learner within the PPN, which directly learns pair-wised relationships for pair proposal generation. Through extensive ablation and analysis, our approach significantly improves upon leveraging the segmenter solid baseline. Notably, our method achieves over 10\% absolute gains compared to our baseline, PSGFormer. The code of this paper is publicly available at https://github.com/king159/Pair-Net.