mlsanityData to 7 Oct 2026

FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training

arXiv 2210.04845 ↗First posted 10 Oct 2022cs.CV cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

This paper is on Few-Shot Object Detection (FSOD), where given a few templates (examples) depicting a novel class (not seen during training), the goal is to detect all of its occurrences within a set of images. From a practical perspective, an FSOD system must fulfil the following desiderata: (a) it must be used as is, without requiring any fine-tuning at test time, (b) it must be able to process an arbitrary number of novel objects concurrently while supporting an arbitrary number of examples from each class and (c) it must achieve accuracy comparable to a closed system. Towards satisfying (a)-(c), in this work, we make the following contributions: We introduce, for the first time, a simple, yet powerful, few-shot detection transformer (FS-DETR) based on visual prompting that can address both desiderata (a) and (b). Our system builds upon the DETR framework, extending it based on two key ideas: (1) feed the provided visual templates of the novel classes as visual prompts during test time, and (2) ``stamp'' these prompts with pseudo-class embeddings (akin to soft prompting), which are then predicted at the output of the decoder. Importantly, we show that our system is not only more flexible than existing methods, but also, it makes a step towards satisfying desideratum (c). Specifically, it is significantly more accurate than all methods that do not require fine-tuning and even matches and outperforms the current state-of-the-art fine-tuning based methods on the most well-established benchmarks (PASCAL VOC & MSCOCO).

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 48 of its 71 references that are in the map. First posted on arXiv 10 Oct 2022.

Builds on

48 of 71 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2017Mask R-CNNcited by 7,259
  10. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  11. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
36 more
  1. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  6. 2022Visual Prompt Tuningcited by 1,674
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  8. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  9. 2019Contrastive Multiview Codingcited by 1,297
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  11. 2019Objects as Pointscited by 1,172
  12. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  13. 2017Focal Loss for Dense Object Detectioncited by 749
  14. 2021Conditional DETR for Fast Training Convergencecited by 422
  15. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  16. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  17. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  18. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  19. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  20. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  21. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  22. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  23. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  24. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  25. 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
  26. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  27. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  28. 2019One-Shot Object Detection with Co-Attention and Co-Excitationcited by 67
  29. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  30. 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
  31. 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
  32. 2021Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detectioncited by 53
  33. 2021Hallucination Improves Few-Shot Object Detectioncited by 50
  34. 2022Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitationcited by 48
  35. 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
  36. 2021AirDet: Few-Shot Detection without Fine-tuning for Autonomous Explorationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 3; 2025: 8; 2026: 4.

20 papers.

Sort:

By area:

  1. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  2. 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentationcited by 17
  3. 2024Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approachcited by 15
  4. 2023MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimizationcited by 14
  5. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  6. 2025Multi-Perspective Data Augmentation for Few-shot Object Detectioncited by 6
  7. 2025Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detectioncited by 6
  8. 2025Visual Textualization for Image Prompted Object Detectioncited by 6
  9. 2023The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentationcited by 5
  10. 2024Neural Assembler: Learning to Generate Fine-Grained Robotic Assembly Instructions from Multi-View Imagescited by 5
  11. 2025CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusioncited by 4
  12. 2025Exemplar Med-DETR: Toward Generalized and Robust Lesion Detection in Mammogram Images and beyondcited by 2
8 more
  1. 2026Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detectioncited by 2
  2. 2023Decoupled DETR For Few-shot Object Detectioncited by 1
  3. 2025FSMODNet: A Closer Look at Few-Shot Detection in Multispectral Datacited by 1
  4. 2025Towards Single-Source Domain Generalized Object Detection via Causal Visual Promptscited by 1
  5. 2026Rethinking Prototype-based Similarity Learning for Few-Shot Object Detectioncited by 1
  6. 2025Indirect Attention: Turning Context Misalignment into a Featurecited by 0
  7. 2026Comparative Study of Out-of-the-Box Technology for Automatic Target Detection and Recognitioncited by 0
  8. 2026Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETRcited by 0