Data to 7 Oct 2026

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

arXiv 2006.03806 ↗First posted 6 Jun 2020cs.LG stat.MLcited by 72

Not on the map. Why?

Abstract (arXiv)

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have proved to achieve the best performance. Following this vein, in this paper we propose a novel transfer-based method that builds on two successive steps: 1) preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and 2) leveraging this preprocessing using an optimal-transport inspired algorithm (in the case of transductive settings). Using standardized vision benchmarks, we prove the ability of the proposed methodology to achieve state-of-the-art accuracy with various datasets, backbone architectures and few-shot settings.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 31; 2023: 14; 2024: 7; 2025: 1; 2026: 2.

72 papers.

Sort:

By area:

2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
2024Boosting Vision-Language Models with Transductioncited by 36
2022SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classificationcited by 34
2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
2021ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognitioncited by 29
2022Realistic Evaluation of Transductive Few-Shot Learningcited by 26
2022The choice of scaling technique matters for classification performancecited by 25
2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
2022Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Predictioncited by 21
2023Context-Aware Meta-Learningcited by 20
2022EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredientscited by 15

38 more

2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
2021Few-Shot Learning by Integrating Spatial and Frequency Representationcited by 11
2022Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classificationcited by 10
2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
2021Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shiftcited by 9
2022Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inferencecited by 9
2023Prototypes-oriented Transductive Few-shot Learning with Conditional Transportcited by 8
2021Sill-Net: Feature Augmentation with Separated Illumination Representationcited by 7
2022The Self-Optimal-Transport Feature Transformcited by 7
2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
2024Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learningcited by 7
2021Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural networkcited by 6
2021A Survey of Deep Learning for Low-Shot Object Detectioncited by 6
2021Diffusion Mechanism in Residual Neural Network: Theory and Applicationscited by 5
2022When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Frameworkcited by 5
2021Automated Human Cell Classification in Sparse Datasets using Few-Shot Learningcited by 4
2021Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classificationcited by 4
2022Advances in MetaDL: AAAI 2021 challenge and workshopcited by 4
2022Worst Case Matters for Few-Shot Recognitioncited by 4
2022Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learningcited by 4
2022PatchMix Augmentation to Identify Causal Features in Few-shot Learningcited by 4
2023Adaptive manifold for imbalanced transductive few-shot learningcited by 4
2023DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learningcited by 4
2023Meta-DM: Applications of Diffusion Models on Few-Shot Learningcited by 4
2023Transductive Learning for Textual Few-Shot Classification in API-based Embedding Modelscited by 4
2021Improving Classification Accuracy with Graph Filteringcited by 3
2021Modular Adaptation for Cross-Domain Few-Shot Learningcited by 3
2021Few-shot Partial Multi-view Learningcited by 3
2022Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approachcited by 3
2022Dynamic Sub-Cluster-Aware Network for Few-Shot Skin Disease Classificationcited by 3
2023A transductive few-shot learning approach for classification of digital histopathological slides from liver cancercited by 3
2022Model-Agnostic Few-Shot Open-Set Recognitioncited by 2
2022Offline Handwritten Amharic Character Recognition Using Few-shot Learningcited by 2
2022Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learningcited by 2
2022A Statistical Model for Predicting Generalization in Few-Shot Classificationcited by 2
2024Convection-Diffusion Equation: A Theoretically Certified Framework for Neural Networkscited by 2
2024The Balanced-Pairwise-Affinities Feature Transformcited by 2

50 most cited of 72 All 72 (JSON)