首届跨域小样本目标检测挑战赛，13支队伍突破现有性能上限。
NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
- 提出多种跨域小样本检测新方法，应对新领域数据稀缺问题。
- 在开源与闭源设置下均达成当前最优结果，最高精度超基线27%以上。
- 适合关注小样本学习与模型泛化能力的研究者参考。
跨域小样本目标检测（CD-FSOD）在不同领域间应用时对现有目标检测与小样本检测模型构成重大挑战。为推动该方向发展，我们联合NTIRE 2025组织了首届CD-FSOD挑战赛，旨在提升目标检测器在全新目标域上仅用少量标注数据时的性能。比赛吸引152名注册参与者，共42支团队提交方案，最终13支队伍完成有效提交。参赛者从多角度出发，提出多种新颖模型，在开源与闭源两种设置下均取得新的最先进成果。本文综述本次挑战赛整体情况，呈现参赛者提出的解决方案，并总结各队提交的结果。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。