mlsanityData to 7 Oct 2026

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

arXiv 2402.03094 ↗First posted 5 Feb 2024cs.CV cs.LGcited by 43

Not on the map. Why?

Abstract (arXiv)

This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples. While transformer-based open-set detectors, such as DE-ViT, show promise in traditional few-shot object detection, their generalization to CD-FSOD remains unclear: 1) can such open-set detection methods easily generalize to CD-FSOD? 2) If not, how can models be enhanced when facing huge domain gaps? To answer the first question, we employ measures including style, inter-class variance (ICV), and indefinable boundaries (IB) to understand the domain gap. Based on these measures, we establish a new benchmark named CD-FSOD to evaluate object detection methods, revealing that most of the current approaches fail to generalize across domains. Technically, we observe that the performance decline is associated with our proposed measures: style, ICV, and IB. Consequently, we propose several novel modules to address these issues. First, the learnable instance features align initial fixed instances with target categories, enhancing feature distinctiveness. Second, the instance reweighting module assigns higher importance to high-quality instances with slight IB. Third, the domain prompter encourages features resilient to different styles by synthesizing imaginary domains without altering semantic contents. These techniques collectively contribute to the development of the Cross-Domain Vision Transformer for CD-FSOD (CD-ViTO), significantly improving upon the base DE-ViT. Experimental results validate the efficacy of our model.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 51 of its 61 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

51 of 61 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2015Fast R-CNNcited by 2,930
  10. 2016Matching Networks for One Shot Learningcited by 2,246
  11. 2022Visual Prompt Tuningcited by 1,674
  12. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
38 more
  1. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  2. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 612
  3. 2021Domain Generalization with MixStylecited by 563
  4. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  5. 2020Open-Vocabulary Object Detection Using Captionscited by 427
  6. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 339
  7. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  8. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  9. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  10. 2021Concealed Object Detectioncited by 212
  11. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  12. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  13. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  14. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  15. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  16. 2022Exploiting Unlabeled Data with Vision and Language Models for Object Detectioncited by 97
  17. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  18. 2020Adversarial Style Mining for One-Shot Unsupervised Domain Adaptationcited by 64
  19. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  20. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  21. 2020A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysiscited by 57
  22. 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
  23. 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
  24. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  25. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  26. 2020Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognitioncited by 50
  27. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  28. 2023A Closer Look at Few-shot Classification Againcited by 46
  29. 2021Label, Verify, Correct: A Simple Few Shot Object Detection Methodcited by 43
  30. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
  31. 2022AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detectioncited by 25
  32. 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detectioncited by 21
  33. 2022Rethinking Few-Shot Object Detection on a Multi-Domain Benchmarkcited by 17
  34. 2022CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detectioncited by 17
  35. 2022TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learningcited by 16
  36. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  37. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  38. 2023Detect Everything with Few Examplescited by 13

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 19; 2026: 16.

43 papers.

Sort:

By area:

  1. 2024Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Communitycited by 50
  2. 2025Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detectioncited by 24
  3. 2025EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answeringcited by 19
  4. 2025EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmarkcited by 16
  5. 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detectioncited by 14
  6. 2025EarthSynth: Generating Informative Earth Observation with Diffusion Modelscited by 12
  7. 2024Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselvescited by 10
  8. 20253D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detectioncited by 10
  9. 2025No time to train! Training-Free Reference-Based Instance Segmentationcited by 9
  10. 2025Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learningcited by 9
  11. 2024INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuningcited by 8
  12. 2025InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognitioncited by 8
31 more
  1. 2024SpecDETR: A transformer-based hyperspectral point object detection networkcited by 6
  2. 2024Teaching VLMs to Localize Specific Objects from In-context Examplescited by 6
  3. 2024Cross-domain Multi-modal Few-shot Object Detection via Rich Textcited by 5
  4. 2024AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Taskscited by 4
  5. 2025CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusioncited by 4
  6. 2025Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptationcited by 3
  7. 2024Beyond Few-shot Object Detection: A Detailed Surveycited by 2
  8. 2025Analyzing the Impact of Low-Rank Adaptation for Cross-Domain Few-Shot Object Detection in Aerial Imagescited by 2
  9. 2026Cross-modal Proxy Evolving for OOD Detection with Vision-Language Modelscited by 2
  10. 2026FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusioncited by 2
  11. 2026Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detectioncited by 2
  12. 2026Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detectioncited by 2
  13. 2026A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helpscited by 2
  14. 2025OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detectioncited by 1
  15. 2025VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detectioncited by 1
  16. 2025ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognitioncited by 1
  17. 2025Towards Single-Source Domain Generalized Object Detection via Causal Visual Promptscited by 1
  18. 2026Practical Insights into Semi-Supervised Object Detection Approachescited by 1
  19. 2026Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsificationcited by 1
  20. 2026Prompt-Free Universal Region Proposal Networkcited by 1
  21. 2026Rethinking Prototype-based Similarity Learning for Few-Shot Object Detectioncited by 1
  22. 2026Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detectioncited by 1
  23. 2025Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichmentcited by 0
  24. 2025Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognitioncited by 0
  25. 2025Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labelscited by 0
  26. 2026Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptationcited by 0
  27. 2026LAB-Det: Language as a Domain-Invariant Bridge for Training-Free One-Shot Domain Generalization in Object Detectioncited by 0
  28. 2026GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detectioncited by 0
  29. 2026Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detectioncited by 0
  30. 2026The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answeringcited by 0
  31. 2026FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detectioncited by 0