Saved in:
Bibliographic Details
Main Authors: Yang, Ziyan, Kafle, Kushal, Lin, Zhe, Cohen, Scott, Ding, Zhihong, Ordonez, Vicente
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.12910
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929198925348864
author Yang, Ziyan
Kafle, Kushal
Lin, Zhe
Cohen, Scott
Ding, Zhihong
Ordonez, Vicente
author_facet Yang, Ziyan
Kafle, Kushal
Lin, Zhe
Cohen, Scott
Ding, Zhihong
Ordonez, Vicente
contents 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 $\langle$subject, 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 $\langle$subject, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_12910
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data
Yang, Ziyan
Kafle, Kushal
Lin, Zhe
Cohen, Scott
Ding, Zhihong
Ordonez, Vicente
Computer Vision and Pattern Recognition
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 $\langle$subject, 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 $\langle$subject, 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.
title SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.12910