NTIRE 2026挑战赛评估跨域少样本目标检测新方法
The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
- 组织跨域少样本检测竞赛，评测模型在新域下的泛化能力
- 31支队伍参与，19支提交有效结果，共696次提交
- 推动少样本检测在真实场景中迁移性能的提升
跨域少样本目标检测（CD-FSOD）仍是现有检测器与少样本学习方法面临的难题，尤其在不同领域间泛化时。作为NTIRE 2026的一部分，我们举办了第二届CD-FSOD挑战赛，系统评估并推动在标注有限条件下于未见目标域中检测物体的进展。挑战赛吸引了128名注册参与者，共提交696次结果。其中31支队伍积极参赛，19支提交了有效最终结果。参赛者探索了多种策略，提出创新方法，在开源与闭源赛道均突破性能边界。本报告详述了2026年CD-FSOD挑战赛，涵盖提交方法总结及各团队最终结果分析。挑战代码：https://github.com/ohMargin/NTIRE2026_CDFSOD。
原文摘要 · Abstract (English)
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.
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。