mlsanityData to 7 Oct 2026

Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning

arXiv 1905.01102 ↗First posted 3 May 2019cs.CV cs.LGcited by 69

Not on the map. Why?

Abstract (arXiv)

Given an initial recognition model already trained on a set of base classes, the goal of this work is to develop a meta-model for few-shot learning. The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new model that can correctly classify in a unified way both the novel and the base classes. To accomplish this goal it must learn to output the appropriate classification weight vectors for those two types of classes. To build our meta-model we make use of two main innovations: we propose the use of a Denoising Autoencoder network (DAE) that (during training) takes as input a set of classification weights corrupted with Gaussian noise and learns to reconstruct the target-discriminative classification weights. In this case, the injected noise on the classification weights serves the role of regularizing the weight generating meta-model. Furthermore, in order to capture the co-dependencies between different classes in a given task instance of our meta-model, we propose to implement the DAE model as a Graph Neural Network (GNN). In order to verify the efficacy of our approach, we extensively evaluate it on ImageNet based few-shot benchmarks and we report strong results that surpass prior approaches. The code and models of our paper will be published on: https://github.com/gidariss/wDAE_GNN_FewShot

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 25; 2023: 9; 2024: 4; 2025: 4; 2026: 1.

69 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  3. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 95
  4. 2021Relational Embedding for Few-Shot Classificationcited by 74
  5. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 70
  6. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  7. 2021Accelerating Large Scale Real-Time GNN Inference using Channel Pruningcited by 41
  8. 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
  9. 2022Few-Shot Classification with Contrastive Learningcited by 31
  10. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  11. 2023MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognitioncited by 26
  12. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
38 more
  1. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  2. 2022FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-trainingcited by 20
  3. 2021Reinforced Attention for Few-Shot Learning and Beyondcited by 18
  4. 2022Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classificationcited by 16
  5. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  6. 2021SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learningcited by 15
  7. 2021Adaptive Poincar'e Point to Set Distance for Few-Shot Classificationcited by 15
  8. 2023Image-free Classifier Injection for Zero-Shot Classificationcited by 15
  9. 2024Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuningcited by 15
  10. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  11. 2021Disentangled Feature Representation for Few-shot Image Classificationcited by 12
  12. 2022Multi-level Second-order Few-shot Learningcited by 12
  13. 2022Towards Open-Set Text Recognition via Label-to-Prototype Learningcited by 12
  14. 2021ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learningcited by 11
  15. 2021Boosting Few-Shot Classification with View-Learnable Contrastive Learningcited by 11
  16. 2024Few-shot Learner Parameterization by Diffusion Time-stepscited by 11
  17. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
  18. 2021DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Networkcited by 9
  19. 2022FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classificationcited by 9
  20. 2023MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignmentscited by 9
  21. 2022Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Samplingcited by 8
  22. 2023GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensingcited by 8
  23. 2021Few-Shot Video Object Detectioncited by 7
  24. 2021Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classificationcited by 7
  25. 2022RankDNN: Learning to Rank for Few-shot Learningcited by 7
  26. 2021MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samplescited by 6
  27. 2022tSF: Transformer-based Semantic Filter for Few-Shot Learningcited by 6
  28. 2021Diffusion Mechanism in Residual Neural Network: Theory and Applicationscited by 5
  29. 2021Few Shot Activity Recognition Using Variational Inferencecited by 5
  30. 2025Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigationcited by 5
  31. 2022Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learningcited by 4
  32. 2022Worst Case Matters for Few-Shot Recognitioncited by 4
  33. 2022Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulationcited by 4
  34. 2022Kernel Relative-prototype Spectral Filtering for Few-shot Learningcited by 4
  35. 2022PatchMix Augmentation to Identify Causal Features in Few-shot Learningcited by 4
  36. 2022Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approachescited by 4
  37. 2023SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learningcited by 4
  38. 2023Clustered-patch Element Connection for Few-shot Learningcited by 4

50 most cited of 69 All 69 (JSON)