C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909959058358272 |
|---|---|
| author | Wang, Siheng Li, Zhengdao Li, Yanshu Xiao, Canran Zhan, Haibo Yao, Zhengtao Zhang, Xuzhi Kang, Jiale Li, Linshan Liu, Weiming Dong, Zhikang Shen, Jifeng Dong, Junhao Sun, Qiang Koniusz, Piotr |
| author_facet | Wang, Siheng Li, Zhengdao Li, Yanshu Xiao, Canran Zhan, Haibo Yao, Zhengtao Zhang, Xuzhi Kang, Jiale Li, Linshan Liu, Weiming Dong, Zhikang Shen, Jifeng Dong, Junhao Sun, Qiang Koniusz, Piotr |
| contents | Object detection has advanced significantly in the closed-set setting, but real-world deployment remains limited by two challenges: poor generalization to unseen categories and insufficient robustness under adverse conditions. Prior research has explored these issues separately: visible-infrared detection improves robustness but lacks generalization, while open-world detection leverages vision-language alignment strategy for category diversity but struggles under extreme environments. This trade-off leaves robustness and diversity difficult to achieve simultaneously. To mitigate these issues, we propose \textbf{C3-OWD}, a curriculum cross-modal contrastive learning framework that unifies both strengths. Stage~1 enhances robustness by pretraining with RGBT data, while Stage~2 improves generalization via vision-language alignment. To prevent catastrophic forgetting between two stages, we introduce an Exponential Moving Average (EMA) mechanism that theoretically guarantees preservation of pre-stage performance with bounded parameter lag and function consistency. Experiments on FLIR, OV-COCO, and OV-LVIS demonstrate the effectiveness of our approach: C3-OWD achieves $80.1$ AP$^{50}$ on FLIR, $48.6$ AP$^{50}_{\text{Novel}}$ on OV-COCO, and $35.7$ mAP$_r$ on OV-LVIS, establishing competitive performance across both robustness and diversity evaluations. Code available at: https://github.com/justin-herry/C3-OWD.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23316 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection Wang, Siheng Li, Zhengdao Li, Yanshu Xiao, Canran Zhan, Haibo Yao, Zhengtao Zhang, Xuzhi Kang, Jiale Li, Linshan Liu, Weiming Dong, Zhikang Shen, Jifeng Dong, Junhao Sun, Qiang Koniusz, Piotr Computer Vision and Pattern Recognition Object detection has advanced significantly in the closed-set setting, but real-world deployment remains limited by two challenges: poor generalization to unseen categories and insufficient robustness under adverse conditions. Prior research has explored these issues separately: visible-infrared detection improves robustness but lacks generalization, while open-world detection leverages vision-language alignment strategy for category diversity but struggles under extreme environments. This trade-off leaves robustness and diversity difficult to achieve simultaneously. To mitigate these issues, we propose \textbf{C3-OWD}, a curriculum cross-modal contrastive learning framework that unifies both strengths. Stage~1 enhances robustness by pretraining with RGBT data, while Stage~2 improves generalization via vision-language alignment. To prevent catastrophic forgetting between two stages, we introduce an Exponential Moving Average (EMA) mechanism that theoretically guarantees preservation of pre-stage performance with bounded parameter lag and function consistency. Experiments on FLIR, OV-COCO, and OV-LVIS demonstrate the effectiveness of our approach: C3-OWD achieves $80.1$ AP$^{50}$ on FLIR, $48.6$ AP$^{50}_{\text{Novel}}$ on OV-COCO, and $35.7$ mAP$_r$ on OV-LVIS, establishing competitive performance across both robustness and diversity evaluations. Code available at: https://github.com/justin-herry/C3-OWD.git. |
| title | C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.23316 |