Towards Flexible Visual Relationship Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Fangrui, Yang, Jianwei, Jiang, Huaizu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916359075528704
author Zhu, Fangrui
Yang, Jianwei
Jiang, Huaizu
author_facet Zhu, Fangrui
Yang, Jianwei
Jiang, Huaizu
contents Visual relationship understanding has been studied separately in human-object interaction(HOI) detection, scene graph generation(SGG), and referring relationships(RR) tasks. Given the complexity and interconnectedness of these tasks, it is crucial to have a flexible framework that can effectively address these tasks in a cohesive manner. In this work, we propose FleVRS, a single model that seamlessly integrates the above three aspects in standard and promptable visual relationship segmentation, and further possesses the capability for open-vocabulary segmentation to adapt to novel scenarios. FleVRS leverages the synergy between text and image modalities, to ground various types of relationships from images and use textual features from vision-language models to visual conceptual understanding. Empirical validation across various datasets demonstrates that our framework outperforms existing models in standard, promptable, and open-vocabulary tasks, e.g., +1.9 $mAP$ on HICO-DET, +11.4 $Acc$ on VRD, +4.7 $mAP$ on unseen HICO-DET. Our FleVRS represents a significant step towards a more intuitive, comprehensive, and scalable understanding of visual relationships.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08305
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Flexible Visual Relationship Segmentation
Zhu, Fangrui
Yang, Jianwei
Jiang, Huaizu
Computer Vision and Pattern Recognition
Visual relationship understanding has been studied separately in human-object interaction(HOI) detection, scene graph generation(SGG), and referring relationships(RR) tasks. Given the complexity and interconnectedness of these tasks, it is crucial to have a flexible framework that can effectively address these tasks in a cohesive manner. In this work, we propose FleVRS, a single model that seamlessly integrates the above three aspects in standard and promptable visual relationship segmentation, and further possesses the capability for open-vocabulary segmentation to adapt to novel scenarios. FleVRS leverages the synergy between text and image modalities, to ground various types of relationships from images and use textual features from vision-language models to visual conceptual understanding. Empirical validation across various datasets demonstrates that our framework outperforms existing models in standard, promptable, and open-vocabulary tasks, e.g., +1.9 $mAP$ on HICO-DET, +11.4 $Acc$ on VRD, +4.7 $mAP$ on unseen HICO-DET. Our FleVRS represents a significant step towards a more intuitive, comprehensive, and scalable understanding of visual relationships.
title Towards Flexible Visual Relationship Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.08305