The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results

TL;DR

The NTIRE 2026 CD-FSOD Challenge evaluated methods for cross-domain few-shot object detection, highlighting innovative approaches and providing a comprehensive analysis of community progress in this challenging area.

Contribution

This paper presents the second challenge on CD-FSOD, showcasing diverse strategies and analyzing results to advance cross-domain few-shot object detection research.

Findings

128 participants registered, with 19 teams submitting final results.

Participants introduced innovative methods to improve detection in unseen domains.

The challenge provided insights into effective strategies for cross-domain few-shot detection.

Abstract

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.