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.

ProTPS: Prototype-Guided Text Prompt Selection for Continual Learning
Apr 1, 2026Jie Mei, Li-Leng Peng, Keith Fuller +1Continual Learning for VLMs Class-Incremental Learning
University of Washington, Seattle, WA, USA · Alaska Pacific University, Anchorage, Alaska, USA
Dual-Imbalance Continual Learning for Real-World Food Recognition
Mar 31, 2026Xiaoyan Zhang, Jiangpeng HeClass-Incremental Learning Incremental Learning
University of Michigan, Ann Arbor, Michigan, U.S.A · Indiana University, Bloomington, Indiana, U.S.A
When Sensing Varies with Contexts: Context Probing for Tactile Few-Shot Class-Incremental Learning
Mar 26, 2026Yifeng Lin, Aiping Huang, Wenxi Liu +4Class-Incremental Learning Prototype-Based Classification
Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou 350108, China
Bi-CRCL: Bidirectional Conservative-Radical Complementary Learning with Pre-trained Foundation Models for Class-incremental Medical Image Analysis
Mar 24, 2026Xinyao Wu, Zhe Xu, Cheng Chen +3Class-Incremental Learning Medical Image Analysis
Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong, China. · Department of Radiation Oncology, Columbia University Irving Medical Center and Data Science Institute, Columbia University, New York, NY, USA. · Department of Electrical and Electronic Engineering and School of Biomedical Engineering, The University of Hong Kong, Hong Kong, China. +2
Compensating Visual Insufficiency with Stratified Language Guidance for Long-Tail Class Incremental Learning
Mar 23, 2026Xi Wang, Xu Yang, Donghao Sun +1Class-Incremental Learning Incremental Learning
School of Electronic Engineering, Xidian University, Xi'an 710071, China
Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models
Mar 22, 2026Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin VanschorenStorage-Efficient Continual Learning Class-Incremental Learning
AMOR/e Lab, Eindhoven University of Technology
A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
Mar 21, 2026Ling Xiao, Toshihiko YamasakiFine-Grained Image Retrieval Class-Incremental Learning
Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan
Continual Learning for Food Category Classification Dataset: Enhancing Model Adaptability and Performance
Mar 20, 2026Piyush Kaushik Bhattacharyya, Devansh Tomar, Shubham Mishra +6Continual Learning Class-Incremental Learning
School of Computer Engineering, KIIT University, Bhubaneshwar, India
Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection
Mar 19, 2026Ruilin Li, Heming Zou, Xiufeng Yan +4Class-Incremental Learning Representation Learning
Wuhan University · Shanghai Innovation Institute · Tsinghua University +3
HSI Image Enhancement Classification Based on Knowledge Distillation: A Study on Forgetting
Mar 19, 2026Songfeng ZhuClass-Incremental Learning Hyperspectral Image Classification
School of Software Engineering, Henan Polytechnic University, Henan 454000, china
CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds
Mar 16, 2026Vaishnavi Nagabhushana, Kartikay Agrawal, Ayon BorthakurClass-Incremental Learning Spiking Neural Networks
SustainAI Lab, MFSDS&AI, IIT Guwahati
Zero-Forgetting CISS via Dual-Phase Cognitive Cascades
Mar 14, 2026Yuquan Lu, Yifu Guo, Zishan Xu +6Semantic Segmentation Class-Incremental Learning
Sun Yat-sen University · Shanghai Jiao Tong University · Southwest University +3
One Adapter for All: Towards Unified Representation in Step-Imbalanced Class-Incremental Learning
Mar 10, 2026Xiaoyan Zhang, Jiangpeng HeAdapter-Based Continual Learning Class-Incremental Learning
University of Michigan, Ann Arbor, Michigan, U.S.A · Indiana University, Bloomington, Indiana, U.S.A
Routing without Forgetting
Mar 10, 2026Alessio Masano, Giovanni Bellitto, Dipam Goswani +2Online Continual Learning Class-Incremental Learning
University of Catania · Department of Computer Science, Universitat Autònoma de Barcelona Computer Vision Center, Barcelona
Class-Incremental Motion Forecasting
Mar 10, 2026Nicolas Schischka, Nikhil Gosala, B Ravi Kiran +2Class-Incremental Learning Autonomous Driving Perception
Department of Computer Science, University of Freiburg, Germany. · Qualcomm SARL France. · Automated Driving, Qualcomm Technologies, Inc.
Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning
Mar 10, 2026Zhen Zhang, Jielei Chu, Jiangtao Hu +4Class-Incremental Learning Catastrophic Forgetting
School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China. · Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, Sichuan 611756, China · National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, Sichuan 611756, China. +2
Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning
Mar 9, 2026Adrian Garcia-Castañeda, Jon Irureta, Jon Imaz +1Storage-Efficient Continual Learning Class-Incremental Learning
Ikerlan Technology Research Center, Arrasate, Spain · Goi Eskola Politeknikoa, Mondragon Unibertsitatea, Arrasate, Spain · University of the Basque Country UPV/EHU, Spain
AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition
Mar 8, 2026Yuchuan Wu, Yinglian Zhu, Haiyang Yu +3Optical Character Recognition Class-Incremental Learning
Fudan University, Shanghai, China
SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation
Mar 6, 2026Vishal Thengane, Zhaochong An, Tianjin Huang +5Few-Shot Semantic Segmentation 3D Semantic Segmentation
University of Surrey, UK · University of Wollongong, Australia · University of Copenhagen, Denmark +2
SPRINT: Semi-supervised Prototypical Representation for Few-Shot Class-Incremental Tabular Learning
Mar 4, 2026Umid Suleymanov, Murat Kantarcioglu, Kevin S Chan +6Class-Incremental Learning Tabular ML
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA · Department of Computer Science, University of Texas at Dallas, Dallas, TX, USA · DEVCOM Army Research Laboratory, Adelphi, MD, USA +1
Dream2Learn: Structured Generative Dreaming for Continual Learning
Mar 2, 2026Salvatore Calcagno, Matteo Pennisi, Federica Proietto Salanitri +4Class-Incremental Learning Self-Training
PeRCeiVe Lab, University of Catania, Italy
Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection
Mar 2, 2026Yaoteng Zhang, Zhou Qing, Junyu Gao +1Object Detection Class-Incremental Learning
Northwestern Polytechnical University
Better Matching, Less Forgetting: A Quality-Guided Matcher for Transformer-based Incremental Object Detection
Mar 2, 2026Qirui Wu, Shizhou Zhang, De Cheng +4Object Detection Class-Incremental Learning
ASGO, School of Computer Science, Northwestern Polytechnical University, China · School of Telecommunications Engineering, Xidian University, China · CCAI, Zhejiang University, China +1
Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning
Mar 2, 2026Jinge Ma, Fengqing ZhuClass-Incremental Learning Catastrophic Forgetting
Purdue University, West Lafayette, Indiana, U.S.A.
From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
Feb 24, 2026Ruiqi Liu, Boyu Diao, Hangda Liu +3Adapter-Based Continual Learning Class-Incremental Learning
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
Catastrophic Forgetting Resilient One-Shot Incremental Federated Learning
Feb 19, 2026Obaidullah Zaland, Zulfiqar Ahmad Khan, Monowar BhuyanFederated Learning Federated Continual Learning
Department of Computing Science, Umeå University, Umeå, SE-90187, Sweden
SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning
Feb 16, 2026Shishir Muralidhara, Didier Stricker, René SchusterTask-Free Continual Learning Continual Learning
German Research Center for Artificial Intelligence (DFKI) · RPTU – University of Kaiserslautern-Landau, Kaiserslautern
Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning
Jan 29, 2026Ruiqi Liu, Boyu Diao, Zijia An +3Class-Incremental Learning Activation Sparsity
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
Nov 19, 2025Tao Hu, Lan Li, Zhen-Hao Xie +1Class-Incremental Learning Continual Learning for VLMs
School of Artificial Intelligence, Nanjing University · State Key Laboratory for Novel Software Technology, Nanjing University
BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning
Nov 14, 2025Lan Li, Tao Hu, Da-Wei Zhou +3Class-Incremental Learning VLM Adaptation
School of Artificial Intelligence, Nanjing University, China · National Key Laboratory for Novel Software Technology, Nanjing University, China

Apr 1, 2026J/K move · Enter open · S save

ProTPS: Prototype-Guided Text Prompt Selection for Continual Learning

Jie Mei, Li-Leng Peng, Keith Fuller, Jenq-Neng Hwang

University of Washington, Seattle, WA, USA · Alaska Pacific University, Anchorage, Alaska, USA

Continual Learning for VLMs Class-Incremental Learning Prompt Learning Domain-Incremental Learning

Open paper AskPDF arXiv

For continual learning, text-prompt-based methods leverage text encoders and learnable prompts to encode semantic features for sequentially arrived classes over time. A common challenge encountered by existing works is how to learn unique text prompts, which implicitly carry semantic information of new classes, so that the semantic features of newly arrived classes do not overlap with those of trained classes, thereby mitigating the catastrophic forgetting problem. To address this challenge, we propose a novel approach Prototype-guided Text Prompt Selection (ProTPS)'' to intentionally increase the training flexibility thus encouraging the learning of unique text prompts. Specifically, our ProTPS learns class-specific vision prototypes and text prompts. Vision prototypes guide the selection and learning of text prompts for each class. We first evaluate our ProTPS in both class incremental (CI) setting and cross-datasets continual (CDC) learning setting. Because our ProTPS achieves performance close to the upper bounds, we further collect a real-world dataset with 112 marine species collected over a span of six years, named Marine112, to bring new challenges to the community. Marine112 is authentically suited for the class and domain incremental (CDI) learning setting and is under natural long-tail distribution. The results under three settings show that our ProTPS performs favorably against the recent state-of-the-art methods. The implementation code and Marine112 dataset will be released upon the acceptance of our paper.