mlsanityData to 7 Oct 2026

Associative Alignment for Few-shot Image Classification

arXiv 1912.05094 ↗First posted 11 Dec 2019cs.CV cs.LGcited by 58

Not on the map. Why?

Abstract (arXiv)

Few-shot image classification aims at training a model from only a few examples for each of the "novel" classes. This paper proposes the idea of associative alignment for leveraging part of the base data by aligning the novel training instances to the closely related ones in the base training set. This expands the size of the effective novel training set by adding extra "related base" instances to the few novel ones, thereby allowing a constructive fine-tuning. We propose two associative alignment strategies: 1) a metric-learning loss for minimizing the distance between related base samples and the centroid of novel instances in the feature space, and 2) a conditional adversarial alignment loss based on the Wasserstein distance. Experiments on four standard datasets and three backbones demonstrate that combining our centroid-based alignment loss results in absolute accuracy improvements of 4.4%, 1.2%, and 6.2% in 5-shot learning over the state of the art for object recognition, fine-grained classification, and cross-domain adaptation, respectively.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 17; 2023: 11; 2024: 6; 2025: 1; 2026: 1.

58 papers.

Sort:

By area:

  1. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  2. 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
  3. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  4. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  5. 2022Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignmentcited by 29
  6. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  7. 2021Binocular Mutual Learning for Improving Few-shot Classificationcited by 26
  8. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  9. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  10. 2022Self-Promoted Supervision for Few-Shot Transformercited by 22
  11. 2022Task Discrepancy Maximization for Fine-grained Few-Shot Classificationcited by 21
  12. 2023Learning Expressive Prompting With Residuals for Vision Transformerscited by 21
38 more
  1. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
  2. 2021Learning to Affiliate: Mutual Centralized Learning for Few-shot Classificationcited by 18
  3. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  4. 2021SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learningcited by 15
  5. 2021Hybrid Graph Neural Networks for Few-Shot Learningcited by 15
  6. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14
  7. 2021MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learningcited by 11
  8. 2021Label Hallucination for Few-Shot Classificationcited by 11
  9. 2022Cap2Aug: Caption guided Image to Image data Augmentationcited by 10
  10. 2021DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Networkcited by 9
  11. 2022CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classificationcited by 9
  12. 2021Multi-level Metric Learning for Few-shot Image Recognitioncited by 8
  13. 2021Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Imagescited by 8
  14. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  15. 2021Prototype Completion for Few-Shot Learningcited by 7
  16. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
  17. 2022tSF: Transformer-based Semantic Filter for Few-Shot Learningcited by 6
  18. 2021Contextualizing Meta-Learning via Learning to Decomposecited by 5
  19. 2021Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstructioncited by 5
  20. 2022When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Frameworkcited by 5
  21. 2022Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognitioncited by 5
  22. 2021Local Propagation for Few-Shot Learningcited by 4
  23. 2022Worst Case Matters for Few-Shot Recognitioncited by 4
  24. 2022PatchMix Augmentation to Identify Causal Features in Few-shot Learningcited by 4
  25. 2023DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlationcited by 4
  26. 2023Task-Oriented Channel Attention for Fine-Grained Few-Shot Classificationcited by 4
  27. 2021Gaussian Process Meta Few-shot Classifier Learning via Linear Discriminant Laplace Approximationcited by 3
  28. 2023Few-shot Classification via Ensemble Learning with Multi-Order Statisticscited by 3
  29. 2024KNN Transformer with Pyramid Prompts for Few-Shot Learningcited by 3
  30. 2023FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?cited by 2
  31. 2021Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shiftcited by 1
  32. 2021Learning Class-level Prototypes for Few-shot Learningcited by 1
  33. 2022BaseTransformers: Attention over base data-points for One Shot Learningcited by 1
  34. 2023LPN: Language-guided Prototypical Network for few-shot classificationcited by 1
  35. 2023Detail Reinforcement Diffusion Model: Augmentation Fine-Grained Visual Categorization in Few-Shot Conditionscited by 1
  36. 2024Intra-task Mutual Attention based Vision Transformer for Few-Shot Learningcited by 1
  37. 2024Tiny models from tiny data: Textual and null-text inversion for few-shot distillationcited by 1
  38. 2024Harnessing the Power of Local Representations for Few-Shot Classificationcited by 1

50 most cited of 58 All 58 (JSON)