Cover Image

NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Yuqian, Qiu, Xingyu, Ren, Bin, Fu, Yanwei, Timofte, Radu, Sebe, Nicu, Yang, Ming-Hsuan, Van Gool, Luc, Zhang, Kaijin, Nong, Qingpeng, Dong, Xiugang, Gao, Hong, Zhou, Xiangsheng, Pan, Jiancheng, Liu, Yanxing, He, Xiao, Li, Jiahao, Sun, Yuze, Huang, Xiaomeng, Zhang, Zhenyu, Ma, Ran, Liu, Yuhan, Zhuang, Zijian, Yi, Shuai, Zou, Yixiong, Hong, Lingyi, Chen, Mingxi, Li, Runze, Sheng, Xingdong, Zhang, Wenqiang, Chen, Weisen, Yan, Yongxin, Chen, Xinguo, Shao, Yuanjie, Zuo, Zhengrong, Sang, Nong, Wu, Hao, Sun, Haoran, Hu, Shuming, Zhang, Yan, Shi, Zhiguang, Zhang, Yu, Chen, Chao, Wang, Tao, Feng, Da, Zhuo, Linhai, Lin, Ziming, Huang, Yali, Me, Jie, Yang, Yiming, Guo, Mi, Jiu, Mingyuan, Xu, Mingliang, Xiong, Maomao, Zhang, Qunshu, Cao, Xinyu, Yang, Yuqing, Sheng, Dianmo, Zhao, Xuanpu, Li, Zhiyu, Ding, Xuyang, Li, Wenqian
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866909579960385536
author	Fu, Yuqian Qiu, Xingyu Ren, Bin Fu, Yanwei Timofte, Radu Sebe, Nicu Yang, Ming-Hsuan Van Gool, Luc Zhang, Kaijin Nong, Qingpeng Dong, Xiugang Gao, Hong Zhou, Xiangsheng Pan, Jiancheng Liu, Yanxing He, Xiao Li, Jiahao Sun, Yuze Huang, Xiaomeng Zhang, Zhenyu Ma, Ran Liu, Yuhan Zhuang, Zijian Yi, Shuai Zou, Yixiong Hong, Lingyi Chen, Mingxi Li, Runze Sheng, Xingdong Zhang, Wenqiang Chen, Weisen Yan, Yongxin Chen, Xinguo Shao, Yuanjie Zuo, Zhengrong Sang, Nong Wu, Hao Sun, Haoran Hu, Shuming Zhang, Yan Shi, Zhiguang Zhang, Yu Chen, Chao Wang, Tao Feng, Da Zhuo, Linhai Lin, Ziming Huang, Yali Me, Jie Yang, Yiming Guo, Mi Jiu, Mingyuan Xu, Mingliang Xiong, Maomao Zhang, Qunshu Cao, Xinyu Yang, Yuqing Sheng, Dianmo Zhao, Xuanpu Li, Zhiyu Ding, Xuyang Li, Wenqian
author_facet	Fu, Yuqian Qiu, Xingyu Ren, Bin Fu, Yanwei Timofte, Radu Sebe, Nicu Yang, Ming-Hsuan Van Gool, Luc Zhang, Kaijin Nong, Qingpeng Dong, Xiugang Gao, Hong Zhou, Xiangsheng Pan, Jiancheng Liu, Yanxing He, Xiao Li, Jiahao Sun, Yuze Huang, Xiaomeng Zhang, Zhenyu Ma, Ran Liu, Yuhan Zhuang, Zijian Yi, Shuai Zou, Yixiong Hong, Lingyi Chen, Mingxi Li, Runze Sheng, Xingdong Zhang, Wenqiang Chen, Weisen Yan, Yongxin Chen, Xinguo Shao, Yuanjie Zuo, Zhengrong Sang, Nong Wu, Hao Sun, Haoran Hu, Shuming Zhang, Yan Shi, Zhiguang Zhang, Yu Chen, Chao Wang, Tao Feng, Da Zhuo, Linhai Lin, Ziming Huang, Yali Me, Jie Yang, Yiming Guo, Mi Jiu, Mingyuan Xu, Mingliang Xiong, Maomao Zhang, Qunshu Cao, Xinyu Yang, Yuqing Sheng, Dianmo Zhao, Xuanpu Li, Zhiyu Ding, Xuyang Li, Wenqian
contents	Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains. In conjunction with NTIRE 2025, we organized the 1st CD-FSOD Challenge, aiming to advance the performance of current object detectors on entirely novel target domains with only limited labeled data. The challenge attracted 152 registered participants, received submissions from 42 teams, and concluded with 13 teams making valid final submissions. Participants approached the task from diverse perspectives, proposing novel models that achieved new state-of-the-art (SOTA) results under both open-source and closed-source settings. In this report, we present an overview of the 1st NTIRE 2025 CD-FSOD Challenge, highlighting the proposed solutions and summarizing the results submitted by the participants.
format	Preprint
id	arxiv_https___arxiv_org_abs_2504_10685
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results Fu, Yuqian Qiu, Xingyu Ren, Bin Fu, Yanwei Timofte, Radu Sebe, Nicu Yang, Ming-Hsuan Van Gool, Luc Zhang, Kaijin Nong, Qingpeng Dong, Xiugang Gao, Hong Zhou, Xiangsheng Pan, Jiancheng Liu, Yanxing He, Xiao Li, Jiahao Sun, Yuze Huang, Xiaomeng Zhang, Zhenyu Ma, Ran Liu, Yuhan Zhuang, Zijian Yi, Shuai Zou, Yixiong Hong, Lingyi Chen, Mingxi Li, Runze Sheng, Xingdong Zhang, Wenqiang Chen, Weisen Yan, Yongxin Chen, Xinguo Shao, Yuanjie Zuo, Zhengrong Sang, Nong Wu, Hao Sun, Haoran Hu, Shuming Zhang, Yan Shi, Zhiguang Zhang, Yu Chen, Chao Wang, Tao Feng, Da Zhuo, Linhai Lin, Ziming Huang, Yali Me, Jie Yang, Yiming Guo, Mi Jiu, Mingyuan Xu, Mingliang Xiong, Maomao Zhang, Qunshu Cao, Xinyu Yang, Yuqing Sheng, Dianmo Zhao, Xuanpu Li, Zhiyu Ding, Xuyang Li, Wenqian Computer Vision and Pattern Recognition Artificial Intelligence Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains. In conjunction with NTIRE 2025, we organized the 1st CD-FSOD Challenge, aiming to advance the performance of current object detectors on entirely novel target domains with only limited labeled data. The challenge attracted 152 registered participants, received submissions from 42 teams, and concluded with 13 teams making valid final submissions. Participants approached the task from diverse perspectives, proposing novel models that achieved new state-of-the-art (SOTA) results under both open-source and closed-source settings. In this report, we present an overview of the 1st NTIRE 2025 CD-FSOD Challenge, highlighting the proposed solutions and summarizing the results submitted by the participants.
title	NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
topic	Computer Vision and Pattern Recognition Artificial Intelligence
url	https://arxiv.org/abs/2504.10685