The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
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_ | 1866918443895226368 |
|---|---|
| author | Qiu, Xingyu Fu, Yuqian Geng, Jiawei Ren, Bin Pan, Jiancheng Wu, Zongwei Tang, Hao Fu, Yanwei Timofte, Radu Sebe, Nicu Elhoseiny, Mohamed Hong, Lingyi Cheng, Mingxi He, Xingqi Li, Runze Sheng, Xingdong Zhang, Wenqiang Liu, Jiacong Luo, Shu Qin, Yikai Zhao, Yaze Jiang, Yongwei Zou, Yixiong Zhang, Zhe Yang, Yang Li, Kaiyu Fu, Bowen Jiang, Zixuan Li, Ke Qiao, Hui Cao, Xiangyong Yu, Xuanlong Sha, Youyang Liu, Longfei Yang, Di Shen, Xi Go, Kyeongryeol Jang, Taewoong Meesiyawar, Saiprasad Kirasur, Ravi Kulkarni, Rakshita Deshpande, Bhoomi Patil, Harsh Mudenagudi, Uma Hu, Shuming Chen, Chao Wang, Tao Zhou, Wei Xu, Qi Xing, Zhenzhao Zhao, Dandan Xia, Hanzhe Lu, Dongdong Zhang, Zhe Wang, Jingru Huang, Guangwei Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Zhou, Liwei Dou, Bei Wu, Tao Fan, Zekang Liu, Junjie de Senneville, Adhémar Armangeon, Flavien Mengbers Lyu, Yazhe Xin, Zhimeng Zhuang, Zijian Zhu, Hongchun Wang, Li |
| author_facet | Qiu, Xingyu Fu, Yuqian Geng, Jiawei Ren, Bin Pan, Jiancheng Wu, Zongwei Tang, Hao Fu, Yanwei Timofte, Radu Sebe, Nicu Elhoseiny, Mohamed Hong, Lingyi Cheng, Mingxi He, Xingqi Li, Runze Sheng, Xingdong Zhang, Wenqiang Liu, Jiacong Luo, Shu Qin, Yikai Zhao, Yaze Jiang, Yongwei Zou, Yixiong Zhang, Zhe Yang, Yang Li, Kaiyu Fu, Bowen Jiang, Zixuan Li, Ke Qiao, Hui Cao, Xiangyong Yu, Xuanlong Sha, Youyang Liu, Longfei Yang, Di Shen, Xi Go, Kyeongryeol Jang, Taewoong Meesiyawar, Saiprasad Kirasur, Ravi Kulkarni, Rakshita Deshpande, Bhoomi Patil, Harsh Mudenagudi, Uma Hu, Shuming Chen, Chao Wang, Tao Zhou, Wei Xu, Qi Xing, Zhenzhao Zhao, Dandan Xia, Hanzhe Lu, Dongdong Zhang, Zhe Wang, Jingru Huang, Guangwei Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Zhou, Liwei Dou, Bei Wu, Tao Fan, Zekang Liu, Junjie de Senneville, Adhémar Armangeon, Flavien Mengbers Lyu, Yazhe Xin, Zhimeng Zhuang, Zijian Zhu, Hongchun Wang, Li |
| contents | Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across distinct domains. As part of NTIRE 2026, we hosted the second CD-FSOD Challenge to systematically evaluate and promote progress in detecting objects in unseen target domains under limited annotation conditions. The challenge received strong community interest, with 128 registered participants and a total of 696 submissions. Among them, 31 teams actively participated, and 19 teams submitted valid final results. Participants explored a wide range of strategies, introducing innovative methods that push the performance frontier under both open-source and closed-source tracks. This report presents a detailed overview of the NTIRE 2026 CD-FSOD Challenge, including a summary of the submitted approaches and an analysis of the final results across all participating teams. Challenge Codes: https://github.com/ohMargin/NTIRE2026_CDFSOD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11998 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results Qiu, Xingyu Fu, Yuqian Geng, Jiawei Ren, Bin Pan, Jiancheng Wu, Zongwei Tang, Hao Fu, Yanwei Timofte, Radu Sebe, Nicu Elhoseiny, Mohamed Hong, Lingyi Cheng, Mingxi He, Xingqi Li, Runze Sheng, Xingdong Zhang, Wenqiang Liu, Jiacong Luo, Shu Qin, Yikai Zhao, Yaze Jiang, Yongwei Zou, Yixiong Zhang, Zhe Yang, Yang Li, Kaiyu Fu, Bowen Jiang, Zixuan Li, Ke Qiao, Hui Cao, Xiangyong Yu, Xuanlong Sha, Youyang Liu, Longfei Yang, Di Shen, Xi Go, Kyeongryeol Jang, Taewoong Meesiyawar, Saiprasad Kirasur, Ravi Kulkarni, Rakshita Deshpande, Bhoomi Patil, Harsh Mudenagudi, Uma Hu, Shuming Chen, Chao Wang, Tao Zhou, Wei Xu, Qi Xing, Zhenzhao Zhao, Dandan Xia, Hanzhe Lu, Dongdong Zhang, Zhe Wang, Jingru Huang, Guangwei Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Zhou, Liwei Dou, Bei Wu, Tao Fan, Zekang Liu, Junjie de Senneville, Adhémar Armangeon, Flavien Mengbers Lyu, Yazhe Xin, Zhimeng Zhuang, Zijian Zhu, Hongchun Wang, Li Computer Vision and Pattern Recognition Artificial Intelligence Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across distinct domains. As part of NTIRE 2026, we hosted the second CD-FSOD Challenge to systematically evaluate and promote progress in detecting objects in unseen target domains under limited annotation conditions. The challenge received strong community interest, with 128 registered participants and a total of 696 submissions. Among them, 31 teams actively participated, and 19 teams submitted valid final results. Participants explored a wide range of strategies, introducing innovative methods that push the performance frontier under both open-source and closed-source tracks. This report presents a detailed overview of the NTIRE 2026 CD-FSOD Challenge, including a summary of the submitted approaches and an analysis of the final results across all participating teams. Challenge Codes: https://github.com/ohMargin/NTIRE2026_CDFSOD. |
| title | The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.11998 |