mlsanityData to 7 Oct 2026

Few-Shot Image Recognition by Predicting Parameters from Activations

arXiv 1706.03466 ↗First posted 12 Jun 2017cs.CVcited by 122

Not on the map. Why?

Abstract (arXiv)

In this paper, we are interested in the few-shot learning problem. In particular, we focus on a challenging scenario where the number of categories is large and the number of examples per novel category is very limited, e.g. 1, 2, or 3. Motivated by the close relationship between the parameters and the activations in a neural network associated with the same category, we propose a novel method that can adapt a pre-trained neural network to novel categories by directly predicting the parameters from the activations. Zero training is required in adaptation to novel categories, and fast inference is realized by a single forward pass. We evaluate our method by doing few-shot image recognition on the ImageNet dataset, which achieves the state-of-the-art classification accuracy on novel categories by a significant margin while keeping comparable performance on the large-scale categories. We also test our method on the MiniImageNet dataset and it strongly outperforms the previous state-of-the-art methods.

Key facts. Cited by 122 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 55; 2022: 33; 2023: 15; 2024: 14; 2025: 5.

122 papers.

Sort:

By area:

  1. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  2. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  3. 2021On the Role of Neural Collapse in Transfer Learningcited by 100
  4. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  5. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  6. 2021Relational Embedding for Few-Shot Classificationcited by 74
  7. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  8. 2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
  9. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  10. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  11. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  12. 2021Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentationcited by 41
38 more
  1. 2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 36
  2. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  3. 2021A General Descent Aggregation Framework for Gradient-based Bi-level Optimizationcited by 28
  4. 2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
  5. 2021Binocular Mutual Learning for Improving Few-shot Classificationcited by 26
  6. 2024MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognitioncited by 25
  7. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  8. 2022Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detectioncited by 23
  9. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  10. 2021Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learningcited by 22
  11. 2022Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignmentscited by 22
  12. 2024HyperFast: Instant Classification for Tabular Datacited by 22
  13. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  14. 2021Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identificationcited by 19
  15. 2022MetaPrompting: Learning to Learn Better Promptscited by 19
  16. 2021An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Datasetcited by 18
  17. 2021Few-Shot Learning with a Strong Teachercited by 16
  18. 2022HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworkscited by 16
  19. 2022Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classificationcited by 16
  20. 2024SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Modelscited by 16
  21. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  22. 2021On sensitivity of meta-learning to support datacited by 15
  23. 2021SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learningcited by 15
  24. 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15
  25. 2023Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalizationcited by 15
  26. 2022Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregationcited by 14
  27. 2021Few-Shot and Continual Learning with Attentive Independent Mechanismscited by 13
  28. 2023Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identificationcited by 13
  29. 2021The Role of Global Labels in Few-Shot Classification and How to Infer Themcited by 12
  30. 2022Towards Open-Set Text Recognition via Label-to-Prototype Learningcited by 12
  31. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  32. 2021Boosting Few-Shot Classification with View-Learnable Contrastive Learningcited by 11
  33. 2021Adaptive Convolutions with Per-pixel Dynamic Filter Atomcited by 11
  34. 2022A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identificationcited by 11
  35. 2023Towards Task Sampler Learning for Meta-Learningcited by 11
  36. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  37. 2021DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Networkcited by 9
  38. 2023Few-shot Action Recognition with Captioning Foundation Modelscited by 9

50 most cited of 122 All 122 (JSON)