Prototype-Based Classification

Ask about this topic

Overview

Prototype-based classification represents each class with one or more examples, centers, or learned patterns, then predicts by measuring similarity in a feature space. Methods range from nearest-centroid and episodic few-shot learning to learned part prototypes, contrastive alignment, and geometric or distributional models; many use pretrained encoders when labeled data are scarce. The approach is used for few-shot recognition, continual learning, medical and time-series classification, and open-set or out-of-distribution detection, with evaluations spanning settings such as ImageNet-LT, CIFAR, and UEA/UCR time-series benchmarks. A central challenge is that prototypes can become unrepresentative under class variation, imbalance, or domain shift, while improving their interpretability and reliability may trade off against accuracy or depend strongly on the similarity and rejection rules used.

Latest papers

CardsList

76 papers12 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

  1. Approximate Unlearning in Prototype-based-classifiers

    Oct 25, 2026Sreejita Ghosh, Mohammad MohammadiMachine UnlearningMachine Unlearning Evaluation

    UMC Groningen, Groningen, The Netherlands · Technical University of Eindhoven, Eindhoven, The Netherlands · Tilburg University, Tilburg, The Netherlands

  2. Learning Discriminative Prototypes via Boundary Repulsion MixUp for Object Re-Identification

    Oct 25, 2026Athena Psalta, Vasileios Tsironis, Konstantinos KarantzalosPerson Re-IdentificationPrototype-Based Classification

    National Technical University of Athens, Iroon Polytechneiou 9, Athens 15780, Greece

  3. Engram Memory Network: Brain-Inspired Prototype Explanations

    Oct 20, 2026Hyunjun Kim, Myoung Hoon HaPrototype-Based ExplanationExplainable Image Classification

    Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea · Center for Neuroscience-inspired AI, KAIST, Daejeon, South Korea

  4. Prototype-Guided Optimization of Quantum Data Embeddings with Linear Cost

    Oct 17, 2026Seokhoon Jeong, Daniel K. ParkQuantum Data EncodingQuantum Kernel Methods

    Department of Statistics and Data Science Yonsei University Republic of Korea · Department of Statistics and Data Science Department of Applied Statistics Department of Quantum Information Yonsei University Republic of Korea

  5. RSAJEV: Training-Free Abstaining Prototype Memory for Eliminating Silent Hallucination in JEV-Based Remote Sensing Classification

    Oct 11, 2026Man Chen, Antai Chen, Shuai Xu +5Remote Sensing Scene ClassificationVLM Hallucination Mitigation

    School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China, and also with the School of Electrical Automation and Information Engineering, Tianjin University, Tianjin 300072, China, and the State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Huainan 232001, Anhui, China · School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China · School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China, and also with the State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Huainan 232001, Anhui, China +1

  6. ProtoSemImage: Image-Valued Prototypes with Deformable Row Alignment for Interpretable Document Classification

    Oct 8, 2026Mohammad Zare, Pirooz ShamsinejadbabakiText ClassificationPrototype-Based Classification

    Artificial Intelligence Lab at AriooBarzan Engineering Team Shiraz, Iran · Department of Computer Engineering and Information Technology Shiraz University of Technology, Shiraz, Iran

  7. CAP: Codebook-Aligned Prediction for Tokenized Robot Policies

    Oct 6, 2026Haoran Chen, Jingtian Ji, Samuel Wheeler +2Robot Policy LearningRobot Learning

    Toyota Technological Institute at Chicago · Argonne National Laboratory

  8. ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detection

    Oct 5, 2026Elijah Bolluyt, Cristina ComaniciuPrototype-Based ClassificationMahalanobis Distance

    Stevens Institute of Technology, Hoboken, NJ, 07030, USA

  9. A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings

    Oct 1, 2026Sahil KadadekarPrototype-Based ClassificationLLM Evaluation

    New York University

  10. Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning

    Sep 30, 2026Hongwei Zhao, Rui Liu, Yansong LiuClass-Incremental LearningPrototype-Based Classification

    School of Computer Science and Engineering, Beihang University

  11. Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning

    Sep 30, 2026HongWei Zhao, Rui Liu, Yong ChenClass-Incremental LearningPrototype-Based Classification

    Beihang University · Beijing University of Posts and Telecommunications

  12. ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models

    Sep 28, 2026Robert Lampel, Timon Klein, Sebastian SagerPrototype-Based ClassificationClassification

    Department of Mathematics, Otto von Guericke University (Magdeburg, Germany) · Max Planck Institute for Dynamics of Complex Technical Systems (Magdeburg, Germany)

  13. Diverse by Design: Architectural Constraints for Prototype-Based Interpretability

    Sep 23, 2026Xinmiao Lin, Matthew WrightPrototype-Based ClassificationPrototype Learning

    Rochester Institute of Technology

  14. Counting and Covering in Nearest-Neighbour Representations of Boolean Functions

    Sep 19, 2026Martin AnthonyVC DimensionPrototype-Based Classification

    Department of Mathematics London School of Economics and Political Science, London, UK

  15. Skeletal Prototypes on Iterative Nerve Expansions

    Sep 14, 2026Jordan Eckert, Henry SchenckPrototype-Based ClassificationPrototype Learning

    Department of Mathematics and Statistics Auburn University Alabama, USA

  16. Robust Prototypical Networks for Few-Shot Sensor Fault Diagnosis

    Sep 10, 2026Mohammed Ayalew Belay, Amirshayan Haghipour, Pierluigi Salvo RossiPrototype-Based ClassificationFault Detection

    Simula UiB, Bergen, Norway · Dept. of Electronic Systems, NTNU, Trondheim, Norway · Dept. of Gas Technology, SINTEF Energy Research, Trondheim, Norway

  17. Soft Symbol Grounding for Prototypical Concepts

    Sep 10, 2026Marcos Galván-López, Nijesh Upreti, Hiram Calvo +2Prototype-Based ClassificationWeakly Supervised Learning

    Centro de Investigación en Computación, Instituto Politécnico Nacional. · School of Informatics, University of Edinburgh.

  18. What Do Scan-Derived Class Prototypes Add? Disentangling Supervision, Prototype Content and Query Protocol in Recognition over Frozen Foundation Features

    Sep 3, 2026Chenxi Tao, Hong-In Won, Seung-Kyum ChoiPrototype-Based ClassificationVision Foundation Models

    George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, 30332, GA, USA

  19. OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification

    Aug 30, 2026Ilán Carretero, Gustavo Jesús Angulo, Rocío del Amor +1Prototype-Based ClassificationFine-Grained Image Classification

    CVBLab, HumanTech, Universitat Politècnica de València, Valencia, Spain · CMA, Mines Paris, PSL University, Sophia Antipolis, France · Artikode Intelligence S.L., Valencia, Spain

  20. Anatomy-Guided Foundation Model Adaptation with Within-Case Prototype Supervision for Standard Plane Detection in Fetal Ultrasound Blind Sweeps

    Aug 27, 2026Yuzhe ZhaoUltrasound ImagingVision Foundation Model Adaptation

    School of Computing, University of Leeds, Leeds, UK

  21. Hyperbolic Latent Geometry for Tree-Structured Prototype Networks: A Local-vs-Global Trade-off

    Aug 25, 2026Peter Flo, Luca GrossmannLatent Space GeometryNeural Representation Geometry

    Harvard University, Cambridge, MA, USA.

  22. A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification

    Aug 14, 2026Christiaan M. Geldenhuys, Thomas R. NieslerFew-Shot Audio ClassificationPrototype-Based Classification

    Department of Electrical and Electronic Engineering University of Stellenbosch

  23. Class Geometry as Supervision for Sample-Efficient Open-World Detection

    Aug 13, 2026Akash Rao, Zhou Chen, Revanth Reddy Palem +3Open-Vocabulary Object DetectionPrototype-Based Classification

    CSSE Department, Auburn University, Auburn, AL, 36849 · Department of Veterinary Pathobiology, Oklahoma State University, Stillwater, OK, 74078

  24. Exemplar-based objective classification of gust-induced loads across multiple flight conditions

    Aug 12, 2026Paolo Olivucci, Kowshik Srivatsan, David E. RivalPrototype-Based Classification

    Institute of Fluid Mechanics, TU Braunschweig, Hermann-Blenk Str. 37, Braunschweig, 38108, Germany.

  25. Quantum Incremental Learning with Mixed State Prototypes

    Aug 11, 2026Yu Wu, Qianli Zhou, Xinyang Deng +3Class-Incremental LearningPrototype-Based Classification

    School of Electronics and Information, Northwestern Polytechnical University, Xi’an, 710072, China · School of Computer Science and Technology, Northwestern Polytechnical University, Xi’an, 710072, China · School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore 637371 +5

  26. MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor

    Aug 7, 2026Beatrice Alessandra Motetti, Tanguy Dugas du Villard, Matteo Risso +7Prototype-Based ClassificationOn-Device Training

    Politecnico di Torino, Turin, Italy · STMicroelectronics, Cornaredo, Italy

  27. Unleashing the Potential of Vision-Language Models for Generalizable AI-Generated Image Detection

    Aug 5, 2026Weihan Cai, Hao Tan, Zichang Tan +2Prototype-Based ClassificationVision-Language Models

    State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · Sangfor Technologies Inc., Shenzhen 518055, China +1

  28. PNEC-Mamba: Prototype-Guided Positive-Negative Evidence Calibration for Hyperspectral Image Classification

    Aug 3, 2026Mingzhen Xu, Can Xu, Di Wang +2Prototype-Based ClassificationHyperspectral Image Classification

  29. Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement

    Jul 29, 2026Tianyan Deng, Yanxiong Li, Rui Gao +1Few-Shot Audio ClassificationPrototype-Based Classification

    School of Mathematics South China University of Technology Guangzhou, China · School of Electronic and Information Engineering South China University of Technology Guangzhou, China

  30. ProtoPointNet: Prototype-Based Interpretable Classification of 3D Dental Point Clouds with Verifiable Spatial Activations

    Jul 14, 2026George V. Jose, Thao Liang Chiam, Toby Hughes +4Prototype-Based ClassificationPoint Cloud Classification

    Adelaide Dental School, Adelaide University, Adelaide, South Australia, Australia · Australian Institute for Machine Learning, Adelaide University, Adelaide, South Australia, Australia · School of Public Health, Adelaide University, Adelaide, South Australia, Australia