---
title: NTIRE 2026 CD-FSOD Challenge
url: https://www.emergentmind.com/topics/ntire-2026-cd-fsod-challenge
type: topic
---

# NTIRE 2026 CD-FSOD Challenge

The **NTIRE 2026 CD-FSOD Challenge** was the second NTIRE challenge devoted to **Cross-Domain Few-Shot Object Detection (CD-FSOD)**, a setting in which a detector must adapt from a source domain to novel target domains under severe domain shift and with only **1, 5, or 10 labeled examples per novel class**. In the challenge formulation, the source classes and target classes are disjoint, the source and target distributions differ substantially, and performance is measured on unseen target domains using **mean Average Precision (mAP)** and a score that emphasizes the hardest **1-shot** regime [2604.11998]. The challenge inherits its conceptual basis from the original CD-FSOD benchmark, which showed that many standard FSOD methods degrade sharply, and can even underperform a naive fine-tuning baseline, when transferred across visually dissimilar domains [2210.05311]. It also extends the dual-track NTIRE framework introduced in 2025, where a **closed-source** setting isolates adaptation under source restrictions and an **open-source** setting probes the upper bound attainable with foundation models, external data, and broader pretraining [2504.10685].

## 1. Benchmark lineage and problem definition

CD-FSOD is an extension of standard few-shot object detection to settings where the source/base dataset and the target/novel dataset are **visually dissimilar**. The original benchmark paper defined this as a practically important departure from conventional FSOD, where source and target data usually come from a similar visual domain such as COCO/VOC. In CD-FSOD, the source domain is rich in labels, the target domain has only **\(K\)-shot** annotations per class, and the source/target domains are visually dissimilar; the benchmark used **MS COCO** as source and **ArTaxOr**, **UODD**, and **DIOR** as target domains, with evaluation at **\(K = 1, 5, 10\)** using **mAP** [2210.05311].

The empirical importance of this formulation lies in a negative result. The benchmark study evaluated both **meta-learning FSOD approaches** and **fine-tuning FSOD approaches**, including **Meta-RCNN**, **H-GCN**, **Meta Faster R-CNN**, **TFA w/cos**, **FSCE**, and **DeFRCN**, and reported that these methods “tend to fall, and even underperform the naive fine-tuning model” on cross-domain transfer [2210.05311]. The proposed distillation-based EMA teacher-student baseline reached **13.8** average mAP across the three target datasets and three shot settings, versus **11.8** for **DeFRCN**, a **2.0 mAP on average** gain [2210.05311].

This suggests that NTIRE’s CD-FSOD challenges are not merely competitions on a harder FSOD benchmark, but structured evaluations of whether adaptation mechanisms remain valid when **domain mismatch**, **overfitting**, and **extreme data scarcity** occur simultaneously. The first NTIRE challenge in 2025 formalized this into a public benchmark with **open-source** and **closed-source** tracks [2504.10685]; the 2026 edition retained that dual structure and expanded the submission pool and method diversity [2604.11998].

## 2. Task formulation, tracks, and scoring

The NTIRE 2026 challenge follows the CD-FSOD formulation in which the **source classes** \(C_s\) and **target classes** \(C_T\) are disjoint:

$$
C_s \cap C_T = \varnothing
$$

The goal is to train on a source domain and adapt to a novel target domain with only a few support annotations per class. The challenge uses the standard **\(N\)-way \(K\)-shot** protocol, where for each target class the support set contains \(K\) labeled instances, with \(K \in \{1, 5, 10\}\), and the remaining images form the query set [2604.11998].

Two tracks structure the evaluation. In the **closed-source CD-FSOD** track, training is restricted to a fixed source domain, specifically **MS-COCO**. The organizers treat this as the **special track**, with one award for the top team. In the **open-source CD-FSOD** track, participants may use additional data sources, pretraining, foundation models, and other external resources; this is the **main track**, with awards for the top three teams [2604.11998]. The distinction mirrors the 2025 challenge design, where the closed-source track measured adaptation under tighter constraints and the open-source track measured what is achievable when large pretrained models and outside data are allowed [2504.10685].

Evaluation is based on **nine mAP values**:

$$
D1_{1shot}, D1_{5shot}, D1_{10shot},\; D2_{1shot}, D2_{5shot}, D2_{10shot},\; D3_{1shot}, D3_{5shot}, D3_{10shot}
$$

where \(D1, D2, D3\) correspond to the final test datasets. The official ranking score is the weighted average

$$
Score = 2 \cdot avg(D1_{1shot}, D2_{1shot}, D3_{1shot}) + 1 \cdot avg(D1_{5shot}, D2_{5shot}, D3_{5shot}) + 1 \cdot avg(D1_{10shot}, D2_{10shot}, D3_{10shot})
$$

with the **1-shot** condition weighted twice because it is both the hardest and the most practically relevant regime [2604.11998]. This weighting principle had already been established in NTIRE 2025 [2504.10685].

## 3. Domain configuration and dataset regime

The 2026 challenge retains the six **CD-ViTO** validation target domains:

- **ArTaxOr**
- **Clipart1K**
- **DIOR**
- **DeepFish**
- **NEU-DET**
- **UODD**

It then adds **three new unseen test domains** for final evaluation:

- **RUOD**
- **CARPK**
- **CarDD**

These target domains differ from **MS-COCO** in **visual style**, **inter-class variance (ICV)**, and **ambiguous category boundaries (IB)** [2604.11998]. The three final test domains were selected to expose distinct kinds of domain shift: **RUOD** is an underwater-object domain, **CARPK** is an aerial vehicle counting/detection domain, and **CarDD** is a car-damage detection domain [2604.11998].

The 2025 challenge used a related but not identical final test configuration: **DeepFruits**, **CARPK**, and **CarDD** [2504.10685]. This suggests that NTIRE 2026 preserved aerial and car-damage evaluation while refreshing the third hidden domain toward underwater imagery.

The importance of the domain regime is inseparable from the original CD-FSOD diagnosis. In the benchmark paper, the source-to-target similarity order from high to low was **ArTaxOr**, **UODD**, then **DIOR**, and the paper argued that cross-domain transfer difficulty arises because features learned from COCO may not align with target-domain appearance, the support examples are too scarce to correct that mismatch, and methods that rely on tight source-domain assumptions overfit [2210.05311]. NTIRE 2026 generalizes this logic into a broader multi-domain evaluation in which texture, scale, object appearance, and annotation ambiguity all vary across the final test domains [2604.11998].

## 4. Participation and final standings

The second challenge received **128 registered participants** and **696 total submissions**. Among these, **31 teams actively participated**, and **19 teams submitted valid final results**. In the final testing stage, **15 teams** submitted results in the **open-source track** and **4 teams** submitted results in the **closed-source track** [2604.11998].

The most important leaderboard pattern was the separation between tracks: **open-source methods clearly outperformed closed-source methods**, which the report attributes to the use of stronger priors, more data, and larger foundation models [2604.11998].

| Track | Team | Score |
|---|---|---:|
| Open-source | FDUROILab_Lenovo | 217.21 |
| Open-source | CDiscover | 192.79 |
| Open-source | NJUST-KMG | 191.38 |
| Closed-source | FewShotEverything | 134.31 |
| Closed-source | Fusion-Few | 108.48 |
| Closed-source | nudt_0110Dplter | 73.71 |

In the open-source track, the top three teams were **FDUROILab_Lenovo** with **217.21**, **CDiscover** with **192.79**, and **NJUST-KMG** with **191.38**. In the closed-source track, **FewShotEverything** won with **134.31**, followed by **Fusion-Few** with **108.48**, **nudt_0110Dplter** with **73.71**, and **freav** with **69.82** [2604.11998]. The report notes that nearly all open-track teams improved significantly over the **CD-ViTO** baseline, while the large gap between the best open-source and closed-source scores underscores the value of **generative models**, **pseudo-labeling**, and **external pretraining** in this task [2604.11998].

A plausible implication is that NTIRE 2026 functions as two benchmarks at once: one for the practical ceiling of contemporary foundation-model ecosystems, and one for the algorithmic efficiency of adaptation under source-constrained few-shot transfer.

## 5. Leading methods and representative solution families

The top-performing **open-source** method, **FDUROILab_Lenovo**, combined **open-vocabulary detection**, **few-shot fine-tuning**, **target-object cropping and augmentation**, **LLM/VLM-guided label generation**, and **dataset-specific post-processing**. Its three-stage pipeline consisted of object cropping and augmentation, fine-tuning with augmented data, and **Qwen3-VL-235B-A22B**-assisted label generation and post-processing. The team reported that the detector often localized correctly but misclassified objects in the target domain, and therefore used **Qwen3-VL as an auxiliary classifier** for filtering and reclassification [2604.11998].

**CDiscover**, the second-ranked open-source team, used a **domain-adaptive hybrid strategy** with two branches: a **GLIP-based iterative self-training** branch for **dataset2**, and a **Qwen-based generative augmentation** branch for **dataset1** and **dataset3**, trained with **GroundingDINO**. For dataset2, the team treated the setting as one with incomplete annotations and used **GLIP pseudo-labeling** to recover missing objects. For datasets 1 and 3, it used **Qwen image generation** to synthesize domain-specific training data for **GroundingDINO**. The reported optimization included **classification / contrastive loss**, **box \(L_1\) loss**, and **GIoU loss**, with Hungarian matching weights **2.0**, **5.0**, and **2.0**, respectively [2604.11998].

**NJUST-KMG** proposed **ASTER**, a hybrid teacher-guided adaptation framework with a **training-free teacher branch** (**FSOD-VFM**), a **trainable student branch** (**ETS** based on GroundingDINO), a pseudo-label bridge from teacher to student, and **Domain-RAG** augmentation. The teacher side used **UPN proposals**, **SAM2 masks**, **DINOv2 features**, **prototype matching**, and **graph diffusion reweighting**; the student side used **GroundingDINO with Swin-B and BERT** and strong mixed-image augmentation. The team first ran the training-free branch on unlabeled target images, converted high-confidence predictions into **COCO-format pseudo annotations**, and then continued fine-tuning the student with them [2604.11998].

The strongest **closed-source** method, **FewShotEverything**, proposed **AIPR**, combining **training-set data augmentation**, **prototype refinement**, and **iterative pseudo-labeling**. Its three main modules were **TDAM**, which used **Qwen-Image 2.0 + Qwen-VL** to synthesize support-like images and generate pseudo labels; **PRM**, which improved foreground prototype extraction by focusing on semantically relevant object regions; and **IPLM**, which iteratively mined unlabeled target instances, especially for **dataset2** where annotations are incomplete. The architecture used a **DINOv2 ViT-L backbone**, a **Faster R-CNN detector**, and **SGD** with learning rate **0.001** and batch size **16** [2604.11998].

Beyond the top entries, the challenge report documents a wide range of method families. **earth-insights** emphasized support-label quality with **SAM3**, **GroundingDINO**, **Weighted Boxes Fusion (WBF)**, and **Object-Centric Mosaic augmentation**. **Intellindust AI Lab** introduced **ZAP**, which selected the better pseudo-label generator per dataset between **SAM3** and **Qwen3.5-35B-A3B** via a custom **FSOD-mAP** criterion. **SAIDA** built a four-stage pipeline spanning **shot-agnostic domain adaptation**, **shot-dependent iterative fine-tuning**, **diffusion-based data augmentation**, and **final optimization**, using **ZERO**, **GroundingDINO**, **YOLO-E**, **SAM3**, **Qwen3-VL**, **CLIP**, **CapPa**, **LoRA**, and **Qwen-Image** [2604.11998].

Several teams explored training-free or weakly trained variants of foundation-model pipelines. **NTR** used a fully **training-free** combination of **UPN**, **SAM2**, and **DINOv2**, reporting that this setup generalized surprisingly well and sometimes outperformed fine-tuned detectors on unseen domains. **J_G_team** added **negative support features** and **query-adaptive cross-attention prototypes** to a training-free **FSOD-VFM** variant. **WRC** combined **GroundingDINO**, a **visual query library**, **CoOp-style learnable prompts**, and **LoRA**, while also using an **EMA Mean Teacher** for pseudo labels [2604.11998].

Other entries concentrated on explicit classification repair. **French Borelli** decoupled localization from classification, refining class predictions with a separate **vision-only model**, **DINOv3**, and a **Nearest Centroid Classifier (NCC)** loss. **Fusion-Few** introduced **FusionFormer**, with **Object-Background Discrimination (OBD)**, **Object-Object Discrimination (OOD)**, and ensemble classification heads. **nudt_0110Dplter** extended **CD-ViTO** through **multi-scale prototype fusion** and an **enhanced training strategy (ETS)** while adding only **+0.8M trainable parameters** over CD-ViTO [2604.11998].

## 6. Recurring themes, limitations, and research significance

The challenge report identifies several clear patterns. First, **foundation models are central**: many top teams relied on **GroundingDINO**, **DINOv2 / DINOv3**, **SAM2 / SAM3**, **Qwen-family VLMs**, and large generative models such as **Qwen-Image** or **FLUX** [2604.11998]. Second, **pseudo-labeling is extremely important** for recovering missing annotations, augmenting sparse support data, bootstrapping second-stage detectors, and refining localization or classification [2604.11998]. Third, **generative augmentation helps**, especially when it synthesizes backgrounds, support-like images, compositional scenes, or synthetic labels [2604.11998]. Fourth, **classification is often harder than localization**, motivating multimodal reclassification, auxiliary vision-only classifiers, prompt refinement, and prototype alignment [2604.11998]. Fifth, **one-shot remains the hardest regime**, which explains the challenge’s weighted score [2604.11998].

The limitations are equally explicit. **Pseudo-label noise** can severely hurt training, especially on fine-grained categories or incomplete labels. **Prompt engineering is fragile**: good prompts help, but synonym expansion can increase false positives. **Domain shift is dataset-dependent**, so a method effective on one target domain may fail on another. **Overfitting** remains a major risk in low-shot fine-tuning; the report notes that training-free methods sometimes generalize better than carefully tuned detectors. Finally, **closed-source constraints remain hard**, with much lower performance when external priors are unavailable [2604.11998].

These findings are consistent with the original CD-FSOD benchmark diagnosis. The 2022 study argued that standard FSOD methods fail because of **domain mismatch**, **overfitting to the source or small target support set**, the fact that **freezing parameters can hurt**, and the inability of **meta-learning** to solve distant-domain transfer by itself [2210.05311]. NTIRE 2025 and NTIRE 2026 show that the strongest contemporary responses to these issues are no longer limited to detector-head modifications; they combine **pretrained detectors**, **pseudo-labeling**, **prototype recalibration**, **domain adaptation**, **multimodal prompting**, and, in some cases, **training-free vision foundation models** [2504.10685][2604.11998].

This suggests that the NTIRE 2026 CD-FSOD Challenge marks a mature stage in the field’s evolution. The central research question is not simply how to design a few-shot detector, but how to coordinate **foundation models**, **support-set exploitation**, and **adaptation strategies** that remain stable under severe domain mismatch and extreme label scarcity.

Source: https://www.emergentmind.com/topics/ntire-2026-cd-fsod-challenge