OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912950988570624 |
|---|---|
| author | Wang, Leilei Liu, Longfei Shen, Xi Yu, Xuanlong He, Ying Tiffany Yu, Fei Richard Chen, Yingyi |
| author_facet | Wang, Leilei Liu, Longfei Shen, Xi Yu, Xuanlong He, Ying Tiffany Yu, Fei Richard Chen, Yingyi |
| contents | Real-time open-vocabulary object detection (OVOD) is essential for practical deployment in dynamic environments, where models must recognize a large and evolving set of categories under strict latency constraints. Current real-time OVOD methods are predominantly built upon YOLO-style models. In contrast, real-time DETR-based methods still lag behind in terms of inference latency, model lightweightness, and overall performance. In this work, we present OV-DEIM, an end-to-end DETR-style open-vocabulary detector built upon the recent DEIMv2 framework with integrated vision-language modeling for efficient open-vocabulary inference. We further introduce a simple query supplement strategy that improves Fixed AP without compromising inference speed. Beyond architectural improvements, we introduce GridSynthetic, a simple yet effective data augmentation strategy that composes multiple training samples into structured image grids. By exposing the model to richer object co-occurrence patterns and spatial layouts within a single forward pass, GridSynthetic mitigates the negative impact of noisy localization signals on the classification loss and improves semantic discrimination, particularly for rare categories. Extensive experiments demonstrate that OV-DEIM achieves state-of-the-art performance on open-vocabulary detection benchmarks, delivering superior efficiency and notable improvements on challenging rare categories. Code and pretrained models are available at https://github.com/wleilei/OV-DEIM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07022 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation Wang, Leilei Liu, Longfei Shen, Xi Yu, Xuanlong He, Ying Tiffany Yu, Fei Richard Chen, Yingyi Computer Vision and Pattern Recognition Real-time open-vocabulary object detection (OVOD) is essential for practical deployment in dynamic environments, where models must recognize a large and evolving set of categories under strict latency constraints. Current real-time OVOD methods are predominantly built upon YOLO-style models. In contrast, real-time DETR-based methods still lag behind in terms of inference latency, model lightweightness, and overall performance. In this work, we present OV-DEIM, an end-to-end DETR-style open-vocabulary detector built upon the recent DEIMv2 framework with integrated vision-language modeling for efficient open-vocabulary inference. We further introduce a simple query supplement strategy that improves Fixed AP without compromising inference speed. Beyond architectural improvements, we introduce GridSynthetic, a simple yet effective data augmentation strategy that composes multiple training samples into structured image grids. By exposing the model to richer object co-occurrence patterns and spatial layouts within a single forward pass, GridSynthetic mitigates the negative impact of noisy localization signals on the classification loss and improves semantic discrimination, particularly for rare categories. Extensive experiments demonstrate that OV-DEIM achieves state-of-the-art performance on open-vocabulary detection benchmarks, delivering superior efficiency and notable improvements on challenging rare categories. Code and pretrained models are available at https://github.com/wleilei/OV-DEIM. |
| title | OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.07022 |