mlsanityData to 7 Oct 2026

Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning

arXiv 2112.03494 ↗First posted 7 Dec 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Learning and generalizing to novel concepts with few samples (Few-Shot Learning) is still an essential challenge to real-world applications. A principle way of achieving few-shot learning is to realize a model that can rapidly adapt to the context of a given task. Dynamic networks have been shown capable of learning content-adaptive parameters efficiently, making them suitable for few-shot learning. In this paper, we propose to learn the dynamic kernels of a convolution network as a function of the task at hand, enabling faster generalization. To this end, we obtain our dynamic kernels based on the entire task and each sample and develop a mechanism further conditioning on each individual channel and position independently. This results in dynamic kernels that simultaneously attend to the global information whilst also considering minuscule details available. We empirically show that our model improves performance on few-shot classification and detection tasks, achieving a tangible improvement over several baseline models. This includes state-of-the-art results on 4 few-shot classification benchmarks: mini-ImageNet, tiered-ImageNet, CUB and FC100 and competitive results on a few-shot detection dataset: MS COCO-PASCAL-VOC.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 48 of its 67 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

48 of 67 references.

References · 48

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2016Matching Networks for One Shot Learningcited by 2,246
  6. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  7. 2016HyperNetworkscited by 1,003
  8. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  9. 2019A Closer Look at Few-shot Classificationcited by 679
  10. 2016Learning to learn by gradient descent by gradient descentcited by 616
  11. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  12. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
36 more
  1. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  2. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  3. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  4. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 403
  5. 2018Meta-learning with differentiable closed-form solverscited by 395
  6. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  7. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  8. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  9. 2016Dynamic Filter Networkscited by 318
  10. 2018How to train your MAMLcited by 306
  11. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  12. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  13. 2019Cross Attention Network for Few-shot Classificationcited by 218
  14. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  15. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  16. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  17. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  18. 2020FcaNet: Frequency Channel Attention Networkscited by 177
  19. 2017Adaptive Neural Networks for Efficient Inferencecited by 161
  20. 2017Convolutional Networks with Adaptive Inference Graphscited by 147
  21. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  22. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  23. 2019Improved Few-Shot Visual Classificationcited by 114
  24. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  25. 2019Meta-Learning with Warped Gradient Descentcited by 98
  26. 2016Learning feed-forward one-shot learnerscited by 93
  27. 2020Laplacian Regularized Few-Shot Learningcited by 90
  28. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  29. 2021Decoupled Dynamic Filter Networkscited by 52
  30. 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
  31. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  32. 2019An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learningcited by 38
  33. 2021Adaptive Poincar'e Point to Set Distance for Few-Shot Classificationcited by 15
  34. 2017Attentive Recurrent Comparatorscited by 13
  35. 2017Structured Set Matching Networks for One-Shot Part Labelingcited by 6
  36. 2021Learning Online for Unified Segmentation and Tracking Modelscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  2. 2023Few-shot Classification via Ensemble Learning with Multi-Order Statisticscited by 3
  3. 2023GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detectioncited by 0
  4. 2024Like Humans to Few-Shot Learning through Knowledge Permeation of Vision and Textcited by 0