mlsanityData to 7 Oct 2026

Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection

arXiv 2602.18811 ↗First posted 21 Feb 2026cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Cross-Domain Few-Shot Object Detection (CD-FSOD) aims to detect novel classes in unseen target domains given only a few labeled examples. While open-vocabulary detectors built on vision-language models (VLMs) transfer well, they depend almost entirely on text prompts, which encode domain-invariant semantics but miss domain-specific visual information needed for precise localization under few-shot supervision. We propose a dual-branch detector that Learns Multi-modal Prototypes, dubbed LMP, by coupling textual guidance with visual exemplars drawn from the target domain. A Visual Prototype Construction module aggregates class-level prototypes from support RoIs and dynamically generates hard-negative prototypes in query images via jittered boxes, capturing distractors and visually similar backgrounds. In the visual-guided branch, we inject these prototypes into the detection pipeline with components mirrored from the text branch as the starting point for training, while a parallel text-guided branch preserves open-vocabulary semantics. The branches are trained jointly and ensembled at inference by combining semantic abstraction with domain-adaptive details. On six cross-domain benchmark datasets and standard 1/5/10-shot settings, our method achieves state-of-the-art or highly competitive mAP.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 48 of its 61 references that are in the map. First posted on arXiv 21 Feb 2026.

Builds on

48 of 61 references.

References · 48

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  8. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  9. 2021Grounded Language-Image Pre-trainingcited by 1,147
  10. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  11. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  12. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
36 more
  1. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 339
  2. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  3. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  4. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  5. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  6. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  7. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  8. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  9. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  10. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  11. 2020A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysiscited by 57
  12. 2022Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitationcited by 48
  13. 2023Multi-modal Queried Object Detection in the Wildcited by 47
  14. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  15. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
  16. 2022AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detectioncited by 25
  17. 2025NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Resultscited by 25
  18. 2025Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detectioncited by 24
  19. 2023Few-Shot Object Detection via Variational Feature Aggregationcited by 22
  20. 2022FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-trainingcited by 20
  21. 2024Benchmarking In-the-wild Multimodal Disease Recognition and A Versatile Baselinecited by 19
  22. 2022Rethinking Few-Shot Object Detection on a Multi-Domain Benchmarkcited by 17
  23. 2022CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detectioncited by 17
  24. 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detectioncited by 14
  25. 2022Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detectioncited by 12
  26. 2025Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routingcited by 12
  27. 2024Few-Shot Object Detection: Research Advances and Challengescited by 11
  28. 2024DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detectioncited by 11
  29. 2022Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detectioncited by 10
  30. 2024Fine-Grained Prototypes Distillation for Few-Shot Object Detectioncited by 10
  31. 2024FastEdit: Fast Text-Guided Single-Image Editing via Semantic-Aware Diffusion Fine-Tuningcited by 10
  32. 2025Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptationcited by 7
  33. 2025Visual Textualization for Image Prompted Object Detectioncited by 6
  34. 2023Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detectioncited by 4
  35. 2024Track Any Peppers: Weakly Supervised Sweet Pepper Tracking Using VLMscited by 4
  36. 2025CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Accelerating Multimodal Large Language Models with Prior-Corrected Token Reductioncited by 2
  2. 2026Spectral Evolution-Guided Token Pruning in Multimodal Large Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection
  2. 2023Revisiting Few-Shot Object Detection with Vision-Language Models
  3. 2026Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection
  4. 2025Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
  5. 2025Boosting Single-domain Generalized Object Detection via Vision-Language Knowledge Interaction
  6. 2025Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes
  7. 2026DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection
  8. 2025From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning