Class-Incremental Learning

Follow this topic Ask about this topic

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

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

ProDER: A Continual Learning Approach for Fault Classification and Localization in Evolving Smart Grids
Nov 7, 2025Emad Efatinasab, Nahal Azadi, Davide Dalle Pezze +3Replay-Based Continual Learning Prototype-Based Classification
Department of Information Engineering, University of Padova. · School of Computing, Newcastle University.
HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning
Sep 26, 2025Zhen-Hao Xie, Yan Wang, Lan Li +3Class-Incremental Learning Vision-Language Models
School of Artificial Intelligence and the State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
The Bayesian Approach to Continual Learning: An Overview
Jul 11, 2025Tameem AdelTask-Incremental Learning Class-Incremental Learning
NPL, Maxwell Centre, University of Cambridge, JJ Thomson Avenue, Cambridge, CB3 OHE, United Kingdom.
Exploiting Stability-Plasticity Asymmetry in Pretrained Detectors for Incremental Object Detection
Apr 14, 2025Songze Li, Qixing Xu, Tonghua Su +3Class-Incremental Learning Detection Transformer
Harbin Institute of Technology, Harbin, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China · Chongqing Research Institute of HIT, Chongqing, China +2
Stochastic Engrams for Efficient Continual Learning
Mar 27, 2025Isabelle Aguilar, Luis Fernando Herbozo Contreras, Omid KaveheiClass-Incremental Learning Binary Neural Networks
School of Biomedical Engineering, The University of Sydney, NSW, 2006, Australia
EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
Mar 13, 2025Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais +2Class-Incremental Learning Prototype-Based Classification
Media Integration and Communication Center (MICC), University of Florence, Italy · Global Optimization Laboratory, University of Florence, Italy · LAMP Team, Computer Vision Center, Barcelona, Spain +1
AIR: Analytic Imbalance Rectifier for Continual Learning
Aug 19, 2024Di Fang, Yinan Zhu, Zhiping Lin +3Class-Imbalanced Learning Class-Incremental Learning
School of Future Technology, South China University of Technology, Guangzhou, China · Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
Jul 8, 2024Xiaojie Li, Yibo Yang, Jianlong Wu +4Class-Incremental Learning Incremental Learning
School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · King Abdullah University of Science and Technology, Jeddah, Saudi Arabia +1
Federated Class-Incremental Learning with Hierarchical Generative Prototypes
Jun 4, 2024Riccardo Salami, Pietro Buzzega, Matteo Mosconi +2Class-Incremental Learning Prototype-Based Classification
AImageLab - University of Modena and Reggio Emilia, Modena, Italy
Realistic Continual Learning Approach using Pre-trained Models
Apr 11, 2024Nadia Nasri, Carlos Gutiérrez-Álvarez, Sergio Lafuente-Arroyo +2Class-Incremental Learning Continual Learning
University of Alcala, Department of Signal Theory and Communications, GRAM Research group, Alcala de Henares, 28805, Spain · Univesity of Alicante, Department of Computer Science and Artificial Intelligence, San Vicente del Raspeig, 03690, Spain

Nov 7, 2025J/K move · Enter open · S save

ProDER: A Continual Learning Approach for Fault Classification and Localization in Evolving Smart Grids

Emad Efatinasab, Nahal Azadi, Davide Dalle Pezze, Gian Antonio Susto+2

Department of Information Engineering, University of Padova. · School of Computing, Newcastle University.

Replay-Based Continual Learning Prototype-Based Classification Power Systems Class-Incremental Learning Fault Localization Fault Diagnosis+1

Open paper AskPDF arXiv

Data-driven fault diagnosis models for smart grids are usually trained once on a fixed dataset, whereas in operation new fault types appear and monitoring is extended to new grid zones. Retraining from scratch on all accumulated data is costly, while naively updating the model on new data causes catastrophic forgetting. To address this problem, we formulate fault type classification and fault zone localization as continual learning (CL) problems and design four evaluation scenarios on the IEEE 13-node test feeder, three class-incremental and one domain-incremental. We then propose Prototype-based Dark Experience Replay (ProDER), which extends DER++ with prototype attraction and prototype-level repulsion losses that stabilize the feature space, temperature-scaled logit distillation, and a prototype-aware replay memory that retains both core and boundary samples of each class. ProDER achieves the highest accuracy among the tested CL methods in all scenarios, with an average accuracy of 58.2%, 6.6 points above the strongest competing method (DPDMR, 51.6%) and only 3.2 points below joint training (61.4%). Per scenario, it improves over the strongest competitor by 4.2 to 7.4 points and closes the gap to joint training to as little as 1.0 point in fault type classification, while matching it in fault zone localization. Moreover, it remains the best method when the replay buffer is substantially reduced. These results show that prototype-guided replay is an effective, memory-bounded way to keep fault diagnosis models up to date as the grid evolves, while validation on field measurements remains a necessary next step.