Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2024

Abstract

Open-Vocabulary Object Detection (OVOD) aims to detect novel objects beyond a given set of base categories on which the detection model is trained. Recent OVOD methods focus on adapting the image-level pre-trained vision-language models (VLMs), such as CLIP, to a region-level object detection task via, eg., region-level knowledge distillation, regional prompt learning, or region-text pre-training, to expand the detection vocabulary. These methods have demonstrated remarkable performance in recognizing regional visual concepts, but they are weak in exploiting the VLMs' powerful global scene understanding ability learned from the billion-scale image-level text descriptions. This limits their capability in detecting hard objects of small, blurred, or occluded appearance from novel/base categories, whose detection heavily relies on contextual information. To address this, we propose a novel approach, namely Simple Image-level Classification for Context-Aware Detection Scoring (SIC-CADS), to leverage the superior global knowledge yielded from CLIP for complementing the current OVOD models from a global perspective. The core of SIC-CADS is a multi-modal multi-label recognition (MLR) module that learns the object co-occurrence-based contextual information from CLIP to recognize all possible object categories in the scene. These image-level MLR scores can then be utilized to refine the instance-level detection scores of the current OVOD models in detecting those hard objects. This is verified by extensive empirical results on two popular benchmarks, OV-LVIS and OV-COCO, which show that SIC-CADS achieves significant and consistent improvement when combined with different types of OVOD models. Further, SIC-CADS also improves the cross-dataset generalization ability on Objects365 and OpenImages.

Keywords

Open-Vocabulary Object Detection (OVOD), Detection model, Novel objects

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of the 38th AAAI Conference on Artificial Intelligence, AAAI 2024, Vancouver, Canada, February 20-27

Volume

38

First Page

1716

Last Page

1725

ISBN

9781577358879

Identifier

10.1609/aaai.v38i2.27939

Publisher

AAAI

City or Country

Palo Alto, CA

Additional URL

https://doi.org/10.1609/aaai.v38i2.27939

Download

Share

COinS