Class-Incremental Learning

Ask about this topic

Overview

Class-incremental learning trains a model on a sequence of classes, often without task labels at test time, and aims to limit catastrophic forgetting as new categories arrive. Methods include replaying stored or generated examples, regularizing or distilling old knowledge, using class prototypes, and isolating updates with adapters, prompts, or experts; some use pretrained models or analytic updates to reduce training and memory costs. Research spans standard image benchmarks as well as few-shot, long-tailed, online, federated, and structured tasks such as detection and segmentation. A central challenge is balancing adaptation to new classes with retention of old ones under limited memory, changing data distributions, and longer, less predictable task sequences.

Latest papers

CardsList

159 papers28 papers in the last four weeks, up 115% on the four weeks before. 0.2% of all new papers.

  1. CARES: Coverage-Aware Replay Exemplar Selection for Continual Learning

    Oct 23, 2026Arundhati S. Shanbhag, Brian B. Moser, Federico Raue +2Replay-Based Continual LearningExperience Replay

    University of Kaiserslautern-Landau, Germany · German Research Center for Artificial Intelligence, Germany

  2. REDAR: Reinforcement-Driven Adaptive Regularisation for Class Incremental Learning

    Oct 22, 2026Akila Ayanthi, Darshana Priyasad, Tharindu Fernando +3Class-Incremental LearningRegularization-Based Continual Learning

    SAIVT, Queensland University of Technology, Australia · CSIRO Robotics, CSIRO, Australia

  3. Generalizing Multimodal Foundational Models in Context-Driven Class Incremental Learning

    Oct 19, 2026Avi Gupta, Nilotpal Sinha, Vishnu Raj +4Class-Incremental LearningMultimodal Foundation Models

    Indraprastha Institute of Information Technology, Delhi · Dolby Laboratories · Indian Institute of Technology, Kanpur +1

  4. LSA-PAST: Layer-Specific Adaptation and Prototype Transport for Compositional Incremental Learning

    Oct 19, 2026Kyle Stein, Andrew Arash Mahyari, Guillermo Francia +2Incremental LearningClass-Incremental Learning

    University of West Florida, Pensacola, FL, USA · Florida Institute for Human and Machine Cognition, Pensacola, FL, USA · Indiana Univeristy, Bloomington, IN, USA

  5. MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental Learning

    Oct 19, 2026Sungjun Yun, Yonghee Choi, Dong-Jun HanModel CalibrationPost-Hoc Calibration

    Yonsei University

  6. Learning without Overwriting: Structural Knowledge Fusion for Continual Learning

    Oct 18, 2026Kanishk Bakshi, Amitansu Pattanaik, Kathiravan SrinivasanClass-Incremental LearningIncremental Learning

    School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu 632014, India · Defence Geoinformatics Research Establishment, Defence Research and Development Organisation, New Delhi 110054, India

  7. An Impossibility Result for ETF Target Geometry, and an Equinorm Remedy for Imbalanced Analytic Continual Learning

    Oct 17, 2026Berk SezerContinual LearningClass-Incremental Learning

    Middle East Technical University, Türkiye

  8. Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration

    Oct 15, 2026Wenju Sun, Qingyong Li, Boyang Li +4Task-Incremental LearningIncremental Learning

    Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, China, 100044. · College of Computing and Data Science, Nanyang Technological University, Singapore, 639798. · Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry, Wuyi University, Fujian, China, 354300.

  9. MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning

    Oct 14, 2026Junlin Chen, Wenhao Wang, Junchao Xu +5Communication-Efficient Mixture-of-ExpertsClass-Incremental Learning

    Beihang University, Beijing, China · Renmin University of China, Beijing, China · Trine University, Indiana, USA +1

  10. SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning

    Oct 14, 2026Teif Aldaajani, Huda Hakami, Maha A. ThafarRegularization-Based Continual LearningIncremental Learning

    Department of Computer Science, College of Computers and Information Technology, Taif University, Taif, 21944, Saudi Arabia .

  11. Continual Learning without Continual Training

    Oct 7, 2026Nikita Narayanan, Ritham Majumdarr, Sonali ParbhooContinual LearningClass-Incremental Learning

    Imperial College London

  12. AccentCL: Robust Accent Classification with Incremental Expansion

    Oct 5, 2026Mu-Ruei Tseng, Waris Quamer, Ghady Nasrallah +1Class-Incremental LearningAudio Classification

    Department of Computer Science and Engineering Texas A&M University College Station, TX 77840, USA

  13. What Must Replay Preserve? Separating Correctable Bias from Class Correspondence

    Oct 5, 2026BoRen Deng, Xiangyue Ma, Chenglong Li +1Class-Incremental LearningReplay-Based Continual Learning

    Beijing University of Posts and Telecommunications · Beihang University · Beijing University of Technology

  14. When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Data

    Oct 4, 2026Ahmadreza Eslaminia, Klara Nahrstedt, Chenhui ShaoClass-Incremental LearningFederated Continual Learning

    Coordinated Science Laboratory University of Illinois Urbana-Champaign · Dept. of Mechanical Engineering University of Michigan

  15. Learning to Curate What You Generate for Generalizable Few-Shot Class-Incremental Learning

    Oct 4, 2026Junhui Yin, Yuchen Yang, Yilin Yin +6Class-Incremental LearningData Selection

    Beijing University of Posts and Telecommunications, Beijing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · Singapore Management University, Singapore, Singapore

  16. MAGIC: Topology-Aware Analytic Graph Few-Shot Class-Incremental Learning

    Oct 4, 2026Junlin Chen, Yuhan Wang, Xuefei Wang +3Class-Incremental LearningContinual Learning

    Beihang University, Beijing, China

  17. Gated Target Propagation for Compositional Generalization in Continual Learning

    Oct 3, 2026Abdel Mfougouon Njupoun, Colin Bredenberg, Blake Aaron Richards +1Continual LearningCompositional Generalization

    Université de Montr´eal Mila Quebec AI Institute · University of Oregon Mila Quebec AI Institute · McGill University Mila Quebec AI Institute

  18. Selective Backpropagation for Efficient Few-Shot Class-Incremental Learning

    Oct 2, 2026Eeham Khan, Abdulmoumen Al-Atrash, Ali AyubClass-Incremental LearningNeural Network Optimization

    PaInt Lab, Concordia University Montreal, QC, Canada

  19. MuLoRA: Spectrally Balanced Low-Rank Adaptation for Continual Learning

    Oct 1, 2026Junkang LiuContinual LearningLow-Rank Adaptation

    Tianjin University

  20. Do Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders

    Oct 1, 2026Ziyuan GaoProtein Function PredictionClass-Incremental Learning

    Department of Computer Science and Technology, University of Cambridge

  21. 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

  22. 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

  23. Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning

    Sep 30, 2026Hongwei Zhao, Rui Liu, Yansong Liu +2Class-Incremental LearningLow-Rank Adaptation

    School of Computer Science and Engineering, Beihang University · School of Computer Science, Beijing University of Posts and Telecommunications

  24. Visual Branch is What You Need for CLIP-based Class-Incremental Learning

    Sep 29, 2026Tao Hu, Zhen-Hao Xie, Jingcai Guo +2Class-Incremental LearningModality Gap in VLMs

    School of Artificial Intelligence, Nanjing University · State Key Laboratory for Novel Software Technology, Nanjing University · Hong Kong Polytechnic University

  25. Width Expansion as a Method for Class Incremental Learning

    Sep 29, 2026A. L. S. Conde, Y. Elkhatib, C. M. RanieriClass-Incremental LearningDynamic Neural Networks

    Institute of Geosciences and Exact Sciences, São Paulo State University (UNESP), Av. 24-A, 1515, Rio Claro, 13506-692, SP, Brazil · School of Computing Science, University of Glasgow, Glasgow, G12 8QQ, Scotland, United Kingdom

  26. Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time

    Sep 29, 2026Jae-Ho Lee, Min-Yeong Park, Jun-Yeong Moon +2Class-Incremental LearningDomain-Incremental Learning

    Korea University, Seoul, Republic of Korea · Kyung Hee University, Yongin, Republic of Korea

  27. Normative Loss Landscape Navigation: A Trajectory-Based Approach to Mitigating Forgetting in Incremental Learning

    Sep 28, 2026Isabelle Aguilar, Zayn Andre Zainal, Luis Fernando Herbozo Contreras +2Class-Incremental LearningIncremental Learning

  28. Distribution-Conditioned Task Routing for Class-Incremental Learning

    Sep 28, 2026Longhuan Xu, Zhipeng Zhou, Wei Ji +3Class-Incremental LearningClassification

    Nanjing University · Nanyang Technological University · Shanghai Jiao Tong University

  29. Hierarchical Response Preservation for Continual Adaptation of Zero-Shot Graph-Text Models

    Sep 27, 2026Haopeng Zhang, Yuhan Wang, Yubing Su +4Class-Incremental LearningZero-Shot Learning

    School of Computer Science and Engineering, Beihang University Beijing, China · School of Electronic and Information Engineering Beihang University Beijing, China · School of Software, Beihang University Beijing, China

  30. TM-APR: Thermal Temporal-Memory Localization via Analytic Online Adaptation

    Sep 22, 2026Yanshuo Bai, Kanji TanakaClass-Incremental LearningVisual Place Recognition