Open-vocabulary object detection via scene graph discovery

Hengcan Shi, Munawar Hayat, Jianfei Cai

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

In recent years, open-vocabulary (OV) object detection has attracted increasing research attention. Unlike traditional detection, which only recognizes fixed-category objects, OV detection aims to detect objects in an open category set. Previous works often leverage vision-language (VL) training data (e.g., referring grounding data) to recognize OV objects. However, they only use pairs of nouns and individual objects in VL data, while these data usually contain much more information, such as scene graphs, which are also crucial for OV detection. In this paper, we propose a novel Scene-Graph-Based Discovery Network (SGDN) that exploits scene graph cues for OV detection. Firstly, a scene-graph-based decoder (SGDecoder) including sparse scene-graph-guided attention (SSGA) is presented. It captures scene graphs and leverages them to discover OV objects. Secondly, we propose scene-graph-based prediction (SGPred), where we build a scene-graph-based offset regression (SGOR) mechanism to enable mutual enhancement between scene graph extraction and object localization. Thirdly, we design a cross-modal learning mechanism in SGPred. It takes scene graphs as bridges to improve the consistency between cross-modal embeddings for OV object classification. Experiments on COCO and LVIS demonstrate the effectiveness of our approach. Moreover, we show the ability of our model for OV scene graph detection, while previous OV scene graph generation methods cannot tackle this task.

Original languageEnglish
Title of host publicationProceedings of the 31st ACM International Conference on Multimedia
EditorsMukesh K. Saini, Ming-Ching Chang
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages4012-4021
Number of pages10
ISBN (Electronic)9798400701085
DOIs
Publication statusPublished - 2023
EventACM International Conference on Multimedia 2023 - Ottawa, Canada
Duration: 29 Oct 20233 Nov 2023
Conference number: 31st
https://dl.acm.org/doi/proceedings/10.1145/3581783 (Proceedings)
https://www.acmmm2023.org (Website)

Conference

ConferenceACM International Conference on Multimedia 2023
Abbreviated titleMM 2023
Country/TerritoryCanada
CityOttawa
Period29/10/233/11/23
Internet address

Keywords

  • object detection
  • open-vocabulary
  • scene graph
  • vision-language

Cite this