mlsanityData to 14 Oct 2026

Enhancing Few-Shot Image Classification with Unlabelled Examples

arXiv 2006.12245 ↗First posted 17 Jun 2020cs.CV cs.LG stat.MLcited by 32

Not on the map. Why?

Abstract (arXiv)

We develop a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance. Our approach combines a regularized Mahalanobis-distance-based soft k-means clustering procedure with a modified state of the art neural adaptive feature extractor to achieve improved test-time classification accuracy using unlabelled data. We evaluate our method on transductive few-shot learning tasks, in which the goal is to jointly predict labels for query (test) examples given a set of support (training) examples. We achieve state of the art performance on the Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks. All trained models and code have been made publicly available at github.com/plai-group/simple-cnaps.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 12; 2023: 8; 2024: 6; 2025: 4; 2026: 1.

32 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  2. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  3. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 80
  4. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  5. 2022Universal Representations: A Unified Look at Multiple Task and Domain Learningcited by 23
  6. 2024AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learningcited by 22
  7. 2023Context-Aware Meta-Learningcited by 21
  8. 2025Reliable Few-shot Learning under Dual Noisescited by 17
  9. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  10. 2022CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classificationcited by 9
  11. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  12. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
20 more
  1. 2024Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learningcited by 7
  2. 2024BECLR: Batch Enhanced Contrastive Few-Shot Learningcited by 6
  3. 2022Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learningcited by 4
  4. 2022Self-Attention Message Passing for Contrastive Few-Shot Learningcited by 4
  5. 2022Enhancing Few-shot Image Classification with Cosine Transformercited by 4
  6. 2023Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detectioncited by 4
  7. 2023Meta-DM: Applications of Diffusion Models on Few-Shot Learningcited by 4
  8. 2023Neural Fine-Tuning Search for Few-Shot Learningcited by 4
  9. 2023Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classificationcited by 4
  10. 2022Feature Extractor Stacking for Cross-domain Few-shot Learningcited by 2
  11. 2022A Statistical Model for Predicting Generalization in Few-Shot Classificationcited by 2
  12. 2024Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognitioncited by 1
  13. 2024Tiny models from tiny data: Textual and null-text inversion for few-shot distillationcited by 1
  14. 2025Transductive One-Shot Learning Meet Subspace Decompositioncited by 1
  15. 2025FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learningcited by 1
  16. 2022Class-Specific Channel Attention for Few-Shot Learningcited by 0
  17. 2023Few-shot Image Classification based on Gradual Machine Learningcited by 0
  18. 2024Flatness Improves Backbone Generalisation in Few-shot Classificationcited by 0
  19. 2025Task-Level Contrastiveness for Cross-Domain Few-Shot Learningcited by 0
  20. 2026Learning to Recover Task Experts from a Multi-Task Merged Modelcited by 0