Skip to content
OpenTrain AIFor AI Companies

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

Yuqian Fu, Xingyu Qiu, Bin Ren, Yanwei Fu, Radu Timofte +57 morePublished Jun 11, 2025
DOI Publisher
Researcher verdict
Context only
Use as context only
Benchmark evidence
Missing
Not verified yet
Time to first repro
A few days
Plan setup time
Risk flags
1
Review before use

Abstract

Domain fit: AI-adjacent · Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.

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 CDFSOD 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.

Results and benchmarks

Freshness tier: cold
Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains.

Implementation

No direct implementation yet

Maintained implementation evidence is not confirmed for this paper yet.

Use the implementation status and reproduction sections for the current action plan.

Implementation evidence summary
Confidence: low

lovelyqian/NTIRE2025_CDFSOD is the closest maintained adjacent implementation (Matches contextual method/domain keyword: object detection). It is not paper-verified; validate algorithm and evaluation setup against the paper before trusting reported metrics. Community adoption signal: 78 GitHub stars.

Reproduction risks
  • Adjacent implementations are not paper-verified
  • Recommended repository is adjacent and not paper-verified.
  • Adjacent implementation match confidence is low.

Reproduction readiness

Time to first repro: days
Last checked: Aug 24, 2026

No repo

No verified implementation available

  • No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.

Hardware requirements

  • Expect multi-day setup/compute for meaningful reproduction based on current guidance.

Framework baselines

Repositories and ecosystem

Closest related implementations

These are not paper-verified. Use them as reference points when no direct implementation is available.

No additional verified repositories beyond the primary recommendation.

Hugging Face artifacts

No trustworthy direct or curated related Hugging Face artifacts were found yet. Use targeted searches to quickly locate candidate models, datasets, and demos.

Tip: start with models, then check datasets and spaces if you need evaluation data or demos.

Research context

30

Citations

59

References

Tasks

Computer science, Object (grammar), Task (project management), Conjunction (astronomy), Object detection, Detector, Task analysis, Key (lock)

Methods

None detected

Domains

Artificial intelligence, Computer vision, Machine learning, Physics and Astronomy

Evaluation and human feedback data

Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.

Open in HFEPX
Explore similar papers