CVAIApr 14, 2025

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

arXiv:2504.10685v136 citationsh-index: 98Has Code2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Originality Synthesis-oriented
AI Analysis

This addresses the problem of adapting object detectors to new domains with few labeled examples for researchers and practitioners, but it is incremental as it builds on existing CD-FSOD challenges.

The paper organized the first Cross-Domain Few-Shot Object Detection (CD-FSOD) Challenge at NTIRE 2025 to improve object detection performance on novel domains with limited data, attracting 152 participants and resulting in new state-of-the-art methods from 13 teams.

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.

Code Implementations4 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes