mlsanityData to 7 Oct 2026

TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning

arXiv 1905.06549 ↗First posted 16 May 2019cs.LG stat.MLcited by 90

Not on the map. Why?

Abstract (arXiv)

Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning. Here, employing a meta-learning strategy with episode-based training, a network and a set of per-class reference vectors are learned across widely varying tasks. At the same time, for every episode, features in the embedding space are linearly projected into a new space as a form of quick task-specific conditioning. The training loss is obtained based on a distance metric between the query and the reference vectors in the projection space. Excellent generalization results in this way. When tested on the Omniglot, miniImageNet and tieredImageNet datasets, we obtain state of the art classification accuracies under various few-shot scenarios.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 21; 2023: 24; 2024: 6; 2025: 7; 2026: 2.

90 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2021Document-Level Event Argument Extraction by Conditional Generationcited by 154
  3. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  4. 2021Subspace Regularizers for Few-Shot Class Incremental Learningcited by 54
  5. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  6. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 49
  7. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  8. 2023A Closer Look at Few-shot Classification Againcited by 46
  9. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  10. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  11. 2023CLIP-guided Prototype Modulating for Few-shot Action Recognitioncited by 41
  12. 2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 36
38 more
  1. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  2. 2022SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classificationcited by 34
  3. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  4. 2021An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labelingcited by 26
  5. 2022Leveraging Language for Accelerated Learning of Tool Manipulationcited by 26
  6. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  7. 2024MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognitioncited by 25
  8. 2023Boosting Few-shot Action Recognition with Graph-guided Hybrid Matchingcited by 24
  9. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  10. 2022Decomposed Meta-Learning for Few-Shot Named Entity Recognitioncited by 22
  11. 2021Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classificationcited by 18
  12. 2022Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypescited by 17
  13. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  14. 2021A Closer Look at Prototype Classifier for Few-shot Image Classificationcited by 15
  15. 2023ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusioncited by 15
  16. 2021Hierarchical Variational Memory for Few-shot Learning Across Domainscited by 14
  17. 2022Multimodal Prototype-Enhanced Network for Few-Shot Action Recognitioncited by 13
  18. 2022Prompt-Based Metric Learning for Few-Shot NERcited by 12
  19. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  20. 2023HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognitioncited by 12
  21. 2021ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learningcited by 11
  22. 2021Label Hallucination for Few-Shot Classificationcited by 11
  23. 2021Knowledge-Aware Meta-learning for Low-Resource Text Classificationcited by 10
  24. 2023Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancementcited by 10
  25. 2021DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Networkcited by 9
  26. 2023Few-shot Action Recognition with Captioning Foundation Modelscited by 9
  27. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  28. 2021On the Importance of Firth Bias Reduction in Few-Shot Classificationcited by 7
  29. 2021Few-shot Learning for Slot Tagging with Attentive Relational Networkcited by 6
  30. 2021Tensor feature hallucination for few-shot learningcited by 6
  31. 2021Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Fillingcited by 6
  32. 2021MHFC: Multi-Head Feature Collaboration for Few-Shot Learningcited by 6
  33. 2021Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learningcited by 5
  34. 2021MDFM: Multi-Decision Fusing Model for Few-Shot Learningcited by 5
  35. 2022Task-Adaptive Feature Transformer with Semantic Enrichment for Few-Shot Segmentationcited by 5
  36. 2022GCT: Graph Co-Training for Semi-Supervised Few-Shot Learningcited by 5
  37. 2023Few-shot Event Detection: An Empirical Study and a Unified Viewcited by 5
  38. 2024Learning to Obstruct Few-Shot Image Classification over Restricted Classescited by 5

50 most cited of 90 All 90 (JSON)