mlsanityData to 14 Oct 2026

Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection

arXiv 2207.11184 ↗First posted 22 Jul 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Most of existing methods for few-shot object detection follow the fine-tuning paradigm, which potentially assumes that the class-agnostic generalizable knowledge can be learned and transferred implicitly from base classes with abundant samples to novel classes with limited samples via such a two-stage training strategy. However, it is not necessarily true since the object detector can hardly distinguish between class-agnostic knowledge and class-specific knowledge automatically without explicit modeling. In this work we propose to learn three types of class-agnostic commonalities between base and novel classes explicitly: recognition-related semantic commonalities, localization-related semantic commonalities and distribution commonalities. We design a unified distillation framework based on a memory bank, which is able to perform distillation of all three types of commonalities jointly and efficiently. Extensive experiments demonstrate that our method can be readily integrated into most of existing fine-tuning based methods and consistently improve the performance by a large margin.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 42 of its 53 references that are in the map. First posted on arXiv 22 Jul 2022.

Builds on

42 of 53 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2015Fast R-CNNcited by 2,933
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  12. 2014FitNets: Hints for Thin Deep Netscited by 1,653
30 more
  1. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  2. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,077
  3. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  4. 2019Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillationcited by 497
  5. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  6. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  7. 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
  8. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  9. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  10. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  11. 2018Low-Shot Learning from Imaginary Datacited by 181
  12. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  13. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  14. 2020Regularizing Class-wise Predictions via Self-knowledge Distillationcited by 144
  15. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  16. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  17. 2020Self-Knowledge Distillation with Progressive Refinement of Targetscited by 107
  18. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  19. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  20. 2018RepMet: Representative-based metric learning for classification and one-shot object detectioncited by 85
  21. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  22. 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
  23. 2018LSTD: A Low-Shot Transfer Detector for Object Detectioncited by 77
  24. 2019Self-Knowledge Distillation in Natural Language Processingcited by 60
  25. 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
  26. 2021Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detectioncited by 53
  27. 2021Hallucination Improves Few-Shot Object Detectioncited by 50
  28. 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
  29. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  30. 2020Restoring Negative Information in Few-Shot Object Detectioncited by 28

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 1; 2025: 4.

11 papers.

  1. 2023Explore the Power of Synthetic Data on Few-shot Object Detectioncited by 38
  2. 2025Multi-Perspective Data Augmentation for Few-shot Object Detectioncited by 6
  3. 2025Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detectioncited by 6
  4. 2025Visual Textualization for Image Prompted Object Detectioncited by 6
  5. 2023Improved Region Proposal Network for Enhanced Few-Shot Object Detectioncited by 5
  6. 2023Clustered-patch Element Connection for Few-shot Learningcited by 4
  7. 2024CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detectioncited by 1
  8. 2022Activating the Discriminability of Novel Classes for Few-shot Segmentationcited by 0
  9. 2023Re-Scoring Using Image-Language Similarity for Few-Shot Object Detectioncited by 0
  10. 2023GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detectioncited by 0
  11. 2025Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detectioncited by 0