mlsanityData to 7 Oct 2026

Laplacian Regularized Few-Shot Learning

arXiv 2006.15486 ↗First posted 28 Jun 2020cs.LG cs.CV stat.MLcited by 90

Not on the map. Why?

Abstract (arXiv)

We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unary term assigning query samples to the nearest class prototype, and (2) a pairwise Laplacian term encouraging nearby query samples to have consistent label assignments. Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to supervision constraints from the support set. We derive a computationally efficient bound optimizer of a relaxation of our function, which computes independent (parallel) updates for each query sample, while guaranteeing convergence. Following a simple cross-entropy training on the base classes, and without complex meta-learning strategies, we conducted comprehensive experiments over five few-shot learning benchmarks. Our LaplacianShot consistently outperforms state-of-the-art methods by significant margins across different models, settings, and data sets. Furthermore, our transductive inference is very fast, with computational times that are close to inductive inference, and can be used for large-scale few-shot tasks.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 24; 2023: 16; 2024: 13; 2025: 7; 2026: 5.

90 papers.

Sort:

By area:

  1. 2022Parameter-free Online Test-time Adaptationcited by 184
  2. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  3. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  4. 2021Relational Embedding for Few-Shot Classificationcited by 74
  5. 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
  6. 2024Boosting Vision-Language Models with Transductioncited by 36
  7. 2024Transductive Zero-Shot and Few-Shot CLIPcited by 31
  8. 2021Meta Discovery: Learning to Discover Novel Classes given Very Limited Datacited by 30
  9. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  10. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 26
  11. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  12. 2022Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignmentscited by 22
38 more
  1. 2022A Strong Baseline for Generalized Few-Shot Semantic Segmentationcited by 22
  2. 2023Bilevel Fast Scene Adaptation for Low-Light Image Enhancementcited by 22
  3. 2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20
  4. 2021Reinforced Attention for Few-Shot Learning and Beyondcited by 18
  5. 2022EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredientscited by 15
  6. 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15
  7. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  8. 2025Realistic Test-Time Adaptation of Vision-Language Modelscited by 14
  9. 2024Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Datacited by 12
  10. 2021MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learningcited by 11
  11. 2023Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddingscited by 11
  12. 2021MetaDelta: A Meta-Learning System for Few-shot Image Classificationcited by 10
  13. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
  14. 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
  15. 2022Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inferencecited by 9
  16. 2021Nearest Neighbour Few-Shot Learning for Cross-lingual Classificationcited by 8
  17. 2023Prototypes-oriented Transductive Few-shot Learning with Conditional Transportcited by 8
  18. 2024Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classificationcited by 8
  19. 2024Boosting Vision-Language Models for Histopathology Classification: Predict all at oncecited by 8
  20. 2021Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classificationcited by 7
  21. 2021Prototype Completion for Few-Shot Learningcited by 7
  22. 2021Fine-Grained Few Shot Learning with Foreground Object Transformationcited by 7
  23. 2022The Self-Optimal-Transport Feature Transformcited by 7
  24. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
  25. 2021MHFC: Multi-Head Feature Collaboration for Few-Shot Learningcited by 6
  26. 2021Diffusion Mechanism in Residual Neural Network: Theory and Applicationscited by 5
  27. 2021MDFM: Multi-Decision Fusing Model for Few-Shot Learningcited by 5
  28. 2022GCT: Graph Co-Training for Semi-Supervised Few-Shot Learningcited by 5
  29. 2024Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detectioncited by 5
  30. 2025Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignmentcited by 5
  31. 2021Transductive Few-Shot Learning: Clustering is All You Need?cited by 4
  32. 2021Automated Human Cell Classification in Sparse Datasets using Few-Shot Learningcited by 4
  33. 2021Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learningcited by 4
  34. 2022Kernel Relative-prototype Spectral Filtering for Few-shot Learningcited by 4
  35. 2023Adaptive manifold for imbalanced transductive few-shot learningcited by 4
  36. 2023DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learningcited by 4
  37. 2023Transductive Learning for Textual Few-Shot Classification in API-based Embedding Modelscited by 4
  38. 2022Model-Agnostic Few-Shot Open-Set Recognitioncited by 2

50 most cited of 90 All 90 (JSON)