Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method
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_ | 1866911551013781504 |
|---|---|
| author | Xu, Xiaoran Yang, Xiaoshan Yang, Jiangang Xu, Yifan Liu, Jian Xu, Changsheng |
| author_facet | Xu, Xiaoran Yang, Xiaoshan Yang, Jiangang Xu, Yifan Liu, Jian Xu, Changsheng |
| contents | Open-Vocabulary Object Detection (OVOD) has achieved remarkable success in generalizing to novel categories. However, this success often rests on the implicit assumption of domain stationarity. In this work, we provide a principled revisit of the OVOD paradigm, uncovering a fundamental vulnerability: the fragile coupling between visual manifolds and textual embeddings when distribution shifts occur.
We first systematically formalize Domain-Generalized Open-Vocabulary Object Detection (DG-OVOD). Through empirical analysis, we demonstrate that visual shifts do not merely add noise; they cause a collapse of the latent cross-modal space where novel category visual signals detach from their semantic anchors.
Motivated by these insights, we propose Progressive Domain-invariant Cross-modal Alignment (PICA). PICA departs from uniform training by introducing a multi-level ambiguity and signal strength curriculum. It builds adaptive pseudo-word prototypes, refined via sample confidence and visual consistency, to enforce invariant cross-domain modality alignment.
Our findings suggest that OVOD's robustness to domain shifts is intrinsically linked to the stability of the latent cross-modal alignment space. Our work provides both a challenging benchmark and a new perspective on building truly generalizable open-vocabulary systems that extend beyond static laboratory conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27556 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method Xu, Xiaoran Yang, Xiaoshan Yang, Jiangang Xu, Yifan Liu, Jian Xu, Changsheng Computer Vision and Pattern Recognition Open-Vocabulary Object Detection (OVOD) has achieved remarkable success in generalizing to novel categories. However, this success often rests on the implicit assumption of domain stationarity. In this work, we provide a principled revisit of the OVOD paradigm, uncovering a fundamental vulnerability: the fragile coupling between visual manifolds and textual embeddings when distribution shifts occur. We first systematically formalize Domain-Generalized Open-Vocabulary Object Detection (DG-OVOD). Through empirical analysis, we demonstrate that visual shifts do not merely add noise; they cause a collapse of the latent cross-modal space where novel category visual signals detach from their semantic anchors. Motivated by these insights, we propose Progressive Domain-invariant Cross-modal Alignment (PICA). PICA departs from uniform training by introducing a multi-level ambiguity and signal strength curriculum. It builds adaptive pseudo-word prototypes, refined via sample confidence and visual consistency, to enforce invariant cross-domain modality alignment. Our findings suggest that OVOD's robustness to domain shifts is intrinsically linked to the stability of the latent cross-modal alignment space. Our work provides both a challenging benchmark and a new perspective on building truly generalizable open-vocabulary systems that extend beyond static laboratory conditions. |
| title | Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.27556 |