mlsanityData to 7 Oct 2026

Low-shot learning with large-scale diffusion

arXiv 1706.02332 ↗First posted 7 Jun 2017cs.CV cs.LG stat.MLcited by 33

Not on the map. Why?

Abstract (arXiv)

This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time. This setup is often referred to as low-shot learning, where a standard approach is to re-train the last few layers of a convolutional neural network learned on separate classes for which training examples are abundant. We consider a semi-supervised setting based on a large collection of images to support label propagation. This is possible by leveraging the recent advances on large-scale similarity graph construction. We show that despite its conceptual simplicity, scaling label propagation up to hundred millions of images leads to state of the art accuracy in the low-shot learning regime.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 7; 2023: 4; 2024: 4; 2025: 1; 2026: 2.

33 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  3. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  4. 2021Class-Balanced Distillation for Long-Tailed Visual Recognitioncited by 27
  5. 2021Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domaincited by 20
  6. 2021GCNBoost: Artwork Classification by Label Propagation through a Knowledge Graphcited by 11
  7. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  8. 2021On the Importance of Firth Bias Reduction in Few-Shot Classificationcited by 7
  9. 2023Approximating Human-Like Few-shot Learning with GPT-based Compressioncited by 7
  10. 2021MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samplescited by 6
  11. 2024Tuning-free Universally-Supervised Semantic Segmentationcited by 6
  12. 2022Few-Shot Non-Parametric Learning with Deep Latent Variable Modelcited by 5
21 more
  1. 2021Local Propagation for Few-Shot Learningcited by 4
  2. 2021Few-shot Partial Multi-view Learningcited by 3
  3. 2021Progressive Representative Labeling for Deep Semi-Supervised Learningcited by 3
  4. 2021Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifierscited by 3
  5. 2021Ensemble Learning with Manifold-Based Data Splitting for Noisy Label Correctioncited by 2
  6. 2022Cold Start Active Learning Strategies in the Context of Imbalanced Classificationcited by 2
  7. 2022Complementing Semi-Supervised Learning with Uncertainty Quantificationcited by 1
  8. 2023An Extensible Multimodal Multi-task Object Dataset with Materialscited by 1
  9. 2023Text-to-feature diffusion for audio-visual few-shot learningcited by 1
  10. 2024Controllable Relation Disentanglement for Few-Shot Class-Incremental Learningcited by 1
  11. 2024FLIER: Few-shot Language Image Models Embedded with Latent Representationscited by 1
  12. 2021Few-Shot Partial-Label Learningcited by 0
  13. 2021Few-shot Learning with Global Relatedness Decoupled-Distillationcited by 0
  14. 2021External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagerycited by 0
  15. 2022ADT-SSL: Adaptive Dual-Threshold for Semi-Supervised Learningcited by 0
  16. 2022KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensemblescited by 0
  17. 2023Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptationcited by 0
  18. 2024Probability-density-aware Semi-supervised Learningcited by 0
  19. 2025Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Datacited by 0
  20. 2026Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classificationcited by 0
  21. 2026MTSSL: Meta-Thresholding Semi-Supervised Learningcited by 0