Open-Vocabulary Object Detection via Scene Graph Discovery

TL;DR

This paper introduces a novel scene-graph-based network for open-vocabulary object detection that leverages scene graph cues and cross-modal learning to improve detection and scene graph generation, outperforming previous methods.

Contribution

It proposes a new SGDN framework utilizing scene graphs for enhanced open-vocabulary detection and scene graph generation, integrating scene-graph-guided attention and cross-modal learning mechanisms.

Findings

Effective on COCO and LVIS datasets

Outperforms previous open-vocabulary detection methods

Enables open-vocabulary scene graph detection

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.