Prototypical Networks for Few-shot Learning

We propose Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend Prototypical Networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.

• Publication year

  2017

• Venue

  Neural Information Processing Systems

• Publication date

  2017-03-15

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1703.05175
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

  2017cited by this paper
• Matching Networks for One Shot Learning

  2016influential reference
• Optimization as a Model for Few-Shot Learning

  2016cited by this paper
• Synthesized Classifiers for Zero-Shot Learning

  2016cited by this paper
• Zero-Shot Recognition via Structured Prediction

  2016cited by this paper
• A Discriminative Feature Learning Approach for Deep Face Recognition

  2016cited by this paper
• Towards a Neural Statistician

  2016influential reference
• Meta-Learning with Memory-Augmented Neural Networks

  2016cited by this paper
• Learning Deep Representations of Fine-Grained Visual Descriptions

  2016influential reference
• Learning Deep Parsimonious Representations

  2016cited by this paper
• Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions

  2015cited by this paper
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Siamese Neural Networks for One-Shot Image Recognition

  2015cited by this paper
• Metric Learning with Adaptive Density Discrimination

  2015cited by this paper
• Going deeper with convolutions

  2014cited by this paper
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models

  2014cited by this paper
• ImageNet Large Scale Visual Recognition Challenge

  2014influential reference
• Adam: A Method for Stochastic Optimization

  2014influential reference
• Neural Turing Machines

  2014cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Evaluation of output embeddings for fine-grained image classification

  2014cited by this paper
• Auto-Encoding Variational Bayes

  2013cited by this paper
• Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions

  2013influential reference
• Label-Embedding for Attribute-Based Classification

  2013cited by this paper
• Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost

  2013influential reference
• Metric Learning: A Survey

  2013cited by this paper
• A Survey on Metric Learning for Feature Vectors and Structured Data

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• One shot learning of simple visual concepts

  2011cited by this paper
• Caltech-UCSD Birds 200

  2010cited by this paper
• A Deep Non-linear Feature Mapping for Large-Margin kNN Classification

  2009cited by this paper
• Visualizing Data using t-SNE

  2008cited by this paper
• Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure

  2007influential reference
• Distance Metric Learning for Large Margin Nearest Neighbor Classification

  2005cited by this paper
• Clustering with Bregman Divergences

  2005influential reference
• Neighbourhood Components Analysis

  2004influential reference
• Learning from one example through shared densities on transforms

  2000cited by this paper
• Long Short-Term Memory

  1997influential reference

• Batch-of-Thought: Cross-Instance Learning for Enhanced LLM Reasoning

  2026cites this paper
• Federated Learning Under Evolving Distribution Shifts

  2026cites this paper
• MedSetFeat++: An attention-enriched set feature framework for few-shot medical image classification

  2026cites this paper
• Study of Class-Incremental Radio Frequency Fingerprint Recognition Without Storing Exemplars

  2026cites this paper
• Forward-reverse rectification network for real-time few-shot strip steel surface defect classification

  2026cites this paper
• Prototype-guided cyclic federated learning with knowledge distillation

  2026cites this paper
• Leveraging CVAE Encoding for Backdoor Attacks in Few-Shot Learning With Prototypical Networks

  2026influential citation
• A remaining useful life estimation method based on meta contrastive learning

  2026cites this paper
• Prototype learning based hierarchical decoupling for multimodal recommendation

  2026cites this paper
• Meta-Learning Guided Pruning for Few-Shot Plant Pathology on Edge Devices

  2026influential citation
• Rich and cross-fused feature embedding for few-shot point cloud semantic segmentation

  2026cites this paper
• The evolving landscape of few shot learning in medical image diagnosis a scoping review

  2026cites this paper
• Universal Latent Homeomorphic Manifolds: A Framework for Cross-Domain Representation Unification

  2026cites this paper
• Adaptive Saliency based Contextual Metric learning for Few-shot Open-set Recognition

  2026cites this paper
• DepGuard: Depression Recognition and Episode Monitoring System With a Ubiquitous Wrist-Worn Device

  2026cites this paper
• Class-Missing Semi-supervised document key information extraction via synergistic refinement estimation

  2026cites this paper
• VPrWS: Vision transformer-based prototypical network with cross-inductive bias distillation for cross-domain wireless human sensing

  2026cites this paper
• A few-shot learning framework for HVAC fault diagnosis in data centers with minimal data required

  2026cites this paper
• Emerging perspectives on embodied intelligence in future smart manufacturing

  2026cites this paper
• Efficient Intrusion Detection for Edge Network via Multi-Stage Few-Shot Class-Incremental Learning

  2026cites this paper
• Reframing Audio Data Annotation as Domain Adaptation Process: A Multi-Indicator Active Learning Framework

  2026cites this paper
• Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration

  2026cites this paper
• Fedpkd: a federated adaptive prototype knowledge distillation method

  2026cites this paper
• Deep learning framework for aesthetic and biomechanical optimization of dance movements

  2026cites this paper
• Few-shot Class-Incremental Learning via Generative Co-Memory Regularization

  2026cites this paper
• Self-supervised exceptional prototypical network for few-shot grading of gastric intestinal metaplasia.

  2026cites this paper
• Motion-aware multi-level feature fusion for few-shot action recognition

  2026cites this paper
• Combine Meta-Learning With Feature Alignment for Cross-Domain Heterogeneous Hyperspectral Image Classification

  2026cites this paper
• Survey on AI‐Enabled Computer Vision Technologies and Applications for Space Robotic Missions

  2026cites this paper
• Semantic Modulated Prompting for Few-Shot Audio-Visual Classification

  2026cites this paper
• Few-Shot Automatic Modulation Classification via Semi-Supervised Metric Learning and Lightweight Conv-Transformer Model

  2026cites this paper
• Toward Effective and Sustainable Traffic Management With Network Scaling Configuration: A Federated FSL Approach

  2026cites this paper
• Reusability Report: Evaluating the performance of a meta-learning foundation model on predicting the antibacterial activity of natural products

  2026cites this paper
• A 40-nm Training-Inference STT-MRAM Near-Memory Computing Macro for Memory-Augmented Neural Network Acceleration

  2026cites this paper
• Few-Shot Knowledge Graph Completion With Adaptive Negative Sampling Mechanism

  2026cites this paper
• Bridging the gaps: A hierarchical distillation approach to multimodal sentiment analysis with missing modalities

  2026cites this paper
• Few-Shot Recognition Method of MFR Operation Modes via Graph-Based Transductive Prototype Propagation Network

  2026influential citation
• A self-supervised framework for improved generalisability in ultrasound B-mode image segmentation

  2026cites this paper
• Adaptive prototype memory with incremental updates for few-shot image classification

  2026cites this paper
• PFSNet: A prototypical federated siamese network for few-shot cervical cancer detection

  2026cites this paper
• A novel knowledge-informed quadratic neurons residual network for explainable fault diagnosis in few-shot scenarios

  2026cites this paper
• Meta-learning with variational inference for few-shot faults diagnosis of automotive transmission under variable operating conditions

  2026cites this paper
• A regularized deep self-expression feature augmentation network for few-shot unconstrained palmprint recognition

  2026cites this paper
• Multi-label odor profiling of Osmanthus Oolong tea using graph neural networks: Integrating public databases and PTR-TOF-MS-based aroma compound analysis

  2026cites this paper
• Development and Validation of a Wearable Intelligent Telerehabilitation Device for Postoperative Rehabilitation of Chronic Ankle Instability Using a Portable Integrated Sensors System and Few-Shot Learning Algorithm

  2026cites this paper
• P3-FSLNet: A Compact Spatio-Temporal Model With Contrastive Few-Shot Learning for Subject-Independent P300 Detection in Devanagari Script-Based P300 Speller

  2026cites this paper
• Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbations

  2026cites this paper
• Prototype-Aware Contrastive Learning for Few-Shot Fault Diagnosis of Antenna Planetary Reducers Under Time-Varying Speed Conditions

  2026cites this paper
• Open World Knowledge Aided Single-Cell Foundation Model with Robust Cross-Modal Cell-Language Pre-training

  2026cites this paper
• Structural propagation dual-prototype refinement network for few-shot 3D point cloud segmentation

  2026cites this paper
• Federated Learning and Class Imbalances

  2026cites this paper
• A Unified Shape-Aware Foundation Model for Time Series Classification

  2026cites this paper
• Reconstruction Guided Few-shot Network For Remote Sensing Image Classification

  2026cites this paper
• FABRIC: Fashion adaptive Bi-level representation with imbalance-aware curriculum learning

  2026cites this paper
• An inverse synthetic aperture radar imaging framework based on multi-layer networks and heat conduction attention

  2026cites this paper
• UP2D: Uncertainty-aware progressive pseudo-label denoising for source-free domain adaptive medical image segmentation

  2026cites this paper
• An output perturbation method based on few-shot learning with data augmentation for lung cancer classification

  2026cites this paper
• EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers

  2026cites this paper
• SAM-Aug: Leveraging SAM Priors for Few-Shot Parcel Segmentation in Satellite Time Series

  2026cites this paper
• Exploiting Class-agnostic Visual Prior for Few-shot Keypoint Detection

  2026influential citation
• Bridging Domain Gaps With ProtoAlign: Teacher–Student Few-Shot Prototype Alignment for Cross-Domain Spoken Language Recognition

  2026influential citation
• Dual-Branch Prototype Enhancement Network for Few-Shot Hyperspectral Image Classification

  2026cites this paper
• An Open-Set Few-Shot Class Incremental Learning Framework for Specific Emitter Identification

  2026cites this paper
• Towards Trustworthy Dialogue Systems With Advanced Out-of-Scope Intent Detection Model

  2026cites this paper
• An Orthogonal Pseudo-Prototype and Pseudo-Target-Based Method for Few-Shot Class-Incremental Automatic Modulation Recognition

  2026cites this paper
• Multi-Modal Few-Shot Semantic Segmentation Based on Triple Attention Mechanism and Hierarchical Decoding Transformer

  2026cites this paper
• Meta-RFF: Meta-Task Adaptive-Based Few-Shot Open-Set Incremental Learning for RF Fingerprint Recognition

  2026cites this paper
• Fine-Grained Transductive Prototypical Network-Based Few-Shot Signal Modulation Classification Using Coarse Labels

  2026cites this paper
• Multimodal Meta-Learning for Early Rumor Detection Based on Few-Shot Learning

  2026cites this paper
• Global and Local Attention-Based Multiscale Prototypical Network for Few-Shot Learning

  2026influential citation
• Multimodal Affect Perception With Large Language Model Enhancement Network

  2026cites this paper
• Disentangling Domain-Invariant Features From Few Samples for Automatic Modulation Classification

  2026cites this paper
• Temporal Consistency and Variation-Guided Spatio-Temporal Aggregation for Few-Shot Action Recognition

  2026cites this paper
• FCGNN: Fuzzy Cognitive Graph Neural Networks With Concept Evolution for Few-Shot Learning

  2026influential citation
• Cross-Modal Device-Free Radar Sensing With Information Maximization Enhancement and Few-Shot Learning

  2026cites this paper
• UF-CDDFM: A unified framework for code defect detection using multi-modal inputs and few-shot learning

  2026cites this paper
• An interpretable fault diagnosis framework for nuclear power plant via graph representation and multi-task learning

  2026cites this paper
• Retrospective Prototype Network Based on Center Difference Measure for Cross-Machine Few-Shot Fault Diagnosis

  2026cites this paper
• Few-Shot Cross-Domain Fault Diagnosis of Complex Mechanical Equipment Based on Multiangle Taylor Metric

  2026cites this paper
• A hybrid cross-domain few-shot bearing fault diagnosis method combining multi-scale feature association and physical information

  2026cites this paper
• CLAIM: A knowledge-intensive, confidence-based label assignment and integration method for crowdsourced construction image data

  2026cites this paper
• BAP-PR: Boundary-aware prompting progressive reasoning for few-shot named entity recognition

  2026cites this paper
• Emotion Transition Recognition Using Multimodal Physiological Signal Fusion

  2026cites this paper
• I-FCSAM: An integrated framework of few-shot learning and segment anything model for vision-based indoor built environment management

  2026cites this paper
• CrossHypergraph: Consistent High-Order Semantic Network for Few-Shot Image Classification

  2026cites this paper
• FSPT: Foreground Separation Prompt Tuning for Few-Shot Fine-Grained X-Ray Classification

  2026cites this paper
• SCG-FSOD: Semantic Correlation-Guided Few-Shot Object Detection in Remote Sensing Images

  2026cites this paper
• TerraSAP: Spatially Aware Prompt-Based Framework for Few-Shot Class-Incremental Learning in Remote Sensing Image Classification

  2026cites this paper
• A Semisupervised Prototypical Network With Dynamic Threshold Pseudolabeling for Forest Classification

  2026cites this paper
• Dual-Path Federated Learning With Prototype Alignment and Dynamic Logits for Intrusion Detection Incorporating Hybrid Feature–Label Shifts

  2026cites this paper
• Mitigating bias in Few Shot Class Incremental Learning with Feature Augmentation and Logits Mix-up

  2026cites this paper
• Graph Convolutional Domain Adversarial Network for Cross-Domain Few-Shot Rolling Bearing Fault Diagnosis

  2026cites this paper
• Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysis

  2026cites this paper
• MFDPN: A multimodal feature dynamic prototype network for few-Shot malware classification

  2026cites this paper
• Dynamic meta-learning with generative augmentation for cross-lingual Japanese few-shot named entity recognition

  2026cites this paper
• Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures

  2026cites this paper
• Key-Value Pair-Free Continual Learner via Task-Specific Prompt-Prototype

  2026cites this paper
• Few-shot with prototype augmentation for low-resource domains rumor detection

  2026cites this paper
• Readability-Robust Code Summarization via Meta Curriculum Learning

  2026cites this paper
• Heterogeneous GNN-driven and meta-learned architecture for transparent multimodal string similarity estimation

  2026cites this paper