Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Weihao, Wang, Runqi, Duan, Xiaoyue, Zhang, Jinchao, Yang, Ang, Jing, Liping
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914448098197504
author Cao, Weihao
Wang, Runqi
Duan, Xiaoyue
Zhang, Jinchao
Yang, Ang
Jing, Liping
author_facet Cao, Weihao
Wang, Runqi
Duan, Xiaoyue
Zhang, Jinchao
Yang, Ang
Jing, Liping
contents Open-vocabulary object detection (OVOD) enables models to detect any object category, including unseen ones. Benefiting from large-scale pre-training, existing OVOD methods achieve strong detection performance on general scenarios (e.g., OV-COCO) but suffer severe performance drops when transferred to downstream tasks with substantial domain shifts. This degradation stems from the scarcity and weak semantics of category labels in domain-specific task, as well as the inability of existing models to capture auxiliary semantics beyond coarse-grained category label. To address these issues, we propose HSA-DINO, a parameter-efficient semantic augmentation framework for enhancing open-vocabulary object detection. Specifically, we propose a multi-scale prompt bank that leverages image feature pyramids to capture hierarchical semantics and select domain-specific local semantic prompts, progressively enriching textual representations from coarse to fine-grained levels. Furthermore, we introduce a semantic-aware router that dynamically selects the appropriate semantic augmentation strategy during inference, thereby preventing parameter updates from degrading the generalization ability of the pre-trained OVOD model. We evaluate HSA-DINO on OV-COCO, several vertical domain datasets, and modified benchmark settings. The results show that HSA-DINO performs favorably against previous state-of-the-art methods, achieving a superior trade-off between domain adaptability and open-vocabulary generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04444
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection
Cao, Weihao
Wang, Runqi
Duan, Xiaoyue
Zhang, Jinchao
Yang, Ang
Jing, Liping
Computer Vision and Pattern Recognition
Open-vocabulary object detection (OVOD) enables models to detect any object category, including unseen ones. Benefiting from large-scale pre-training, existing OVOD methods achieve strong detection performance on general scenarios (e.g., OV-COCO) but suffer severe performance drops when transferred to downstream tasks with substantial domain shifts. This degradation stems from the scarcity and weak semantics of category labels in domain-specific task, as well as the inability of existing models to capture auxiliary semantics beyond coarse-grained category label. To address these issues, we propose HSA-DINO, a parameter-efficient semantic augmentation framework for enhancing open-vocabulary object detection. Specifically, we propose a multi-scale prompt bank that leverages image feature pyramids to capture hierarchical semantics and select domain-specific local semantic prompts, progressively enriching textual representations from coarse to fine-grained levels. Furthermore, we introduce a semantic-aware router that dynamically selects the appropriate semantic augmentation strategy during inference, thereby preventing parameter updates from degrading the generalization ability of the pre-trained OVOD model. We evaluate HSA-DINO on OV-COCO, several vertical domain datasets, and modified benchmark settings. The results show that HSA-DINO performs favorably against previous state-of-the-art methods, achieving a superior trade-off between domain adaptability and open-vocabulary generalization.
title Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.04444