COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Yupeng, Han, Ruize, Feng, Yuzhong, Ren, Zixin, Tian, Yuntong, Wan, Liang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916050235293696
author Zhang, Yupeng
Han, Ruize
Feng, Yuzhong
Ren, Zixin
Tian, Yuntong
Wan, Liang
author_facet Zhang, Yupeng
Han, Ruize
Feng, Yuzhong
Ren, Zixin
Tian, Yuntong
Wan, Liang
contents Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continually evolve, and existing OVD models still struggle with newly emerging concepts, while repeated full retraining is prohibitively expensive. To this end, we introduce a new task setting, termed Continual OVD with Novel Concept Injection (COVD), where models sequentially learn incoming novel concept groups while preserving prior concepts and original open-vocabulary knowledge, along with a new benchmark, Novel-114. Our key observation is that pretrained visual encoders often already perceive and represent many novel concepts, and the main bottleneck lies in the lack of stable semantic alignment between visual representations and textual concepts. Based on this, we propose NoIn-Det, an efficient continual injection framework without additional parameters. NoIn-Det freezes the visual encoder, preserves the text representation space using only texts of common concepts and previously injected concepts, and injects novel concepts by updating only a small subset of text-branch parameters beneficial to novel concept learning. Extensive experiments show that NoIn-Det effectively learns novel concepts, preserves old knowledge, and consistently outperforms existing continual learning methods for VLMs without introducing additional parameters.Novel-114 and the code will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27116
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
Zhang, Yupeng
Han, Ruize
Feng, Yuzhong
Ren, Zixin
Tian, Yuntong
Wan, Liang
Computer Vision and Pattern Recognition
Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continually evolve, and existing OVD models still struggle with newly emerging concepts, while repeated full retraining is prohibitively expensive. To this end, we introduce a new task setting, termed Continual OVD with Novel Concept Injection (COVD), where models sequentially learn incoming novel concept groups while preserving prior concepts and original open-vocabulary knowledge, along with a new benchmark, Novel-114. Our key observation is that pretrained visual encoders often already perceive and represent many novel concepts, and the main bottleneck lies in the lack of stable semantic alignment between visual representations and textual concepts. Based on this, we propose NoIn-Det, an efficient continual injection framework without additional parameters. NoIn-Det freezes the visual encoder, preserves the text representation space using only texts of common concepts and previously injected concepts, and injects novel concepts by updating only a small subset of text-branch parameters beneficial to novel concept learning. Extensive experiments show that NoIn-Det effectively learns novel concepts, preserves old knowledge, and consistently outperforms existing continual learning methods for VLMs without introducing additional parameters.Novel-114 and the code will be released.
title COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.27116