OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision

TL;DR

This paper introduces OV-DQUO, a novel open-vocabulary detection method that uses denoising text query training and unknown object supervision to improve detection of novel categories, achieving state-of-the-art results.

Contribution

The paper proposes a wildcard matching method and a denoising text query training strategy to enhance open-vocabulary detection, addressing confidence bias and background confusion issues.

Findings

Achieved 45.6 AP50 on OV-COCO benchmark.

Achieved 39.3 mAP on OV-LVIS benchmark.

Outperformed previous methods without extra training data.

Abstract

Open-vocabulary detection aims to detect objects from novel categories beyond the base categories on which the detector is trained. However, existing open-vocabulary detectors trained on base category data tend to assign higher confidence to trained categories and confuse novel categories with the background. To resolve this, we propose OV-DQUO, an \textbf{O}pen-\textbf{V}ocabulary DETR with \textbf{D}enoising text \textbf{Q}uery training and open-world \textbf{U}nknown \textbf{O}bjects supervision. Specifically, we introduce a wildcard matching method. This method enables the detector to learn from pairs of unknown objects recognized by the open-world detector and text embeddings with general semantics, mitigating the confidence bias between base and novel categories. Additionally, we propose a denoising text query training strategy. It synthesizes foreground and background query-box pairs from open-world unknown objects to train the detector through contrastive learning, enhancing its ability to distinguish novel objects from the background. We conducted extensive experiments on the challenging OV-COCO and OV-LVIS benchmarks, achieving new state-of-the-art results of 45.6 AP50 and 39.3 mAP on novel categories respectively, without the need for additional training data. Models and code are released at \url{https://github.com/xiaomoguhz/OV-DQUO}