English

SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data

Computer Vision and Pattern Recognition 2024-01-08 v2

Abstract

We propose Subject-Conditional Relation Detection SCoRD, where conditioned on an input subject, the goal is to predict all its relations to other objects in a scene along with their locations. Based on the Open Images dataset, we propose a challenging OIv6-SCoRD benchmark such that the training and testing splits have a distribution shift in terms of the occurrence statistics of \langlesubject, relation, object\rangle triplets. To solve this problem, we propose an auto-regressive model that given a subject, it predicts its relations, objects, and object locations by casting this output as a sequence of tokens. First, we show that previous scene-graph prediction methods fail to produce as exhaustive an enumeration of relation-object pairs when conditioned on a subject on this benchmark. Particularly, we obtain a recall@3 of 83.8% for our relation-object predictions compared to the 49.75% obtained by a recent scene graph detector. Then, we show improved generalization on both relation-object and object-box predictions by leveraging during training relation-object pairs obtained automatically from textual captions and for which no object-box annotations are available. Particularly, for \langlesubject, relation, object\rangle triplets for which no object locations are available during training, we are able to obtain a recall@3 of 33.80% for relation-object pairs and 26.75% for their box locations.

Keywords

Cite

@article{arxiv.2308.12910,
  title  = {SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data},
  author = {Ziyan Yang and Kushal Kafle and Zhe Lin and Scott Cohen and Zhihong Ding and Vicente Ordonez},
  journal= {arXiv preprint arXiv:2308.12910},
  year   = {2024}
}

Comments

WACV 2024

R2 v1 2026-06-28T12:03:38.693Z