Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries

TL;DR

This paper introduces PST, a novel Transformer-based method that models hierarchical part-and-sum relationships for visual relationship detection and human-object interaction, achieving state-of-the-art results in single-stage models.

Contribution

The paper proposes a new Part-and-Sum detection Transformer (PST) that explicitly models hierarchical part and sum hypotheses with composite queries and attention modules.

Findings

Achieves state-of-the-art results in visual relationship detection.

Nearly matches two-stage models in performance.

Introduces tensor-based and vector-based composite queries.

Abstract

Computer vision applications such as visual relationship detection and human object interaction can be formulated as a composite (structured) set detection problem in which both the parts (subject, object, and predicate) and the sum (triplet as a whole) are to be detected in a hierarchical fashion. In this paper, we present a new approach, denoted Part-and-Sum detection Transformer (PST), to perform end-to-end visual composite set detection. Different from existing Transformers in which queries are at a single level, we simultaneously model the joint part and sum hypotheses/interactions with composite queries and attention modules. We explicitly incorporate sum queries to enable better modeling of the part-and-sum relations that are absent in the standard Transformers. Our approach also uses novel tensor-based part queries and vector-based sum queries, and models their joint interaction. We report experiments on two vision tasks, visual relationship detection and human object interaction and demonstrate that PST achieves state of the art results among single-stage models, while nearly matching the results of custom designed two-stage models.