Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning
School of Computer Science, Nanjing University of Information Science（南京信息工程大学计算机科学学院）；School of Computing, Macquarie University（麦考瑞大学计算机学院）；School of Cybersecurity, Northwestern Polytechnical University（西北工业大学网络安全学院）；School of Computer Science, Nanjing University of Posts（南京邮电大学计算机科学学院）；University of California at Merced（加州大学默塞德分校）
Shengqin Jiang, Xiaoran Feng, Yuankai Qi, Haokui Zhang, Renlong Hang, Qingshan Liu, Lina Yao, Quan Z. Sheng, Ming-Hsuan Yang
Few-shot class-incremental learning (FSCIL) seeks to continuously learn new classes from very limited samples while preserving previously acquired knowledge. Traditional methods often utilize a frozen pre-trained feature extractor to generate static class prototypes, which suffer from the inherent representation bias of the backbone. While recent prompt-based tuning methods attempt to adapt the backbone via minimal parameter updates, given the constraint of extreme data scarcity, the model's capacity to assimilate novel information and substantively enhance its global discriminative power is inherently limited. In this paper, we propose a novel shift in perspective: freezing the feature extractor while fine-tuning the prototypes. We argue that the primary challenge in FSCIL is not feature acquisition, but rather the optimization of decision regions within a static, high-quality feature space. To this end, we introduce an efficient prototype fine-tuning framework that evolves static centroids into dynamic, learnable components. The framework employs a dual-calibration method consisting of class-specific and task-aware offsets. These components function synergistically to improve the discriminative capacity of prototypes for ongoing incremental classes. Extensive results demonstrate that our method attains superior performance across multiple benchmarks while requiring minimal learnable parameters.
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
Department of Computer Science and Artificial Intelligence, DaSCI Institute, University of Granada, Granada, Spain（计算机科学与人工智能系，DaSCI研究所，格拉纳达大学，格拉纳达，西班牙）；Department of Mathematics ``Tullio Levi-Civita'', University of Padova, Padova, Italy（托里利-西维塔数学系，帕多瓦大学，帕多瓦，意大利）
Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学软件新技术国家重点实验室）
University of Chinese Academy of Science（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences (CAS)（中国科学院自动化研究所）
Class incremental learning(CIL) has attracted much attention, but most existing related works focus on fine-tuning the entire representation model, which inevitably results in much catastrophic forgetting. In the contrast, with a semantic-rich pre-trained representation model, parameter-additional-tuning (PAT) only changes very few parameters to learn new visual concepts. Recent studies have proved that PAT-based CIL can naturally avoid fighting against forgetting by replaying or distilling like most of the existing methods. However, we find that PAT-based CIL still faces serious semantic drif…
University of Science and Technology of China（中国科学技术大学）；Huawei Technologies Co. Ltd.（华为技术有限公司）
Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes. It is a challenging task since representation optimization and prototype reorganization can only be achieved under little supervision. To address this problem, we propose a novel incremental prototype learning scheme. Our scheme consists of a random episode selection strategy that adapts the feature representation to various generated incremental episodes to enhance the corresponding extensibility, and a self-promoted prototype refinement mechanism which strengthens the express…
Politecnico di Torino（都灵理工大学）；Italian Institute of Technology（意大利理工学院）；University of Tübingen（图宾根大学）；ETH Zurich（苏黎世联邦理工学院）
Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, constrained to the classes of the training set. Toward addressing both problems, we introduce a new task, Incremental Few-Shot Segmentation (iFSS). The goal of iFSS is to extend a pretrained segmentation model with new classes from few annotated images and without access to old training data. To overcome the limitations of existing models iniFSS, we propose Prototype-based Incremental Few-Shot Segmentation (PIFS) that co…
PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）
Peking University（北京大学）；South China University of Technology（华南理工大学）；National University of Singapore（新加坡国立大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
This paper studies a new, practical but challenging problem, called Class-Incremental Unsupervised Domain Adaptation (CI-UDA), where the labeled source domain contains all classes, but the classes in the unlabeled target domain increase sequentially. This problem is challenging due to two difficulties. First, source and target label sets are inconsistent at each time step, which makes it difficult to conduct accurate domain alignment. Second, previous target classes are unavailable in the current step, resulting in the forgetting of previous knowledge. To address this problem, we propose a nov…
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
Hangzhou Dianzi University（杭州电子科技大学）；Macao Polytechnic University（澳门理工大学）；Beijing Institute of Technology（北京理工大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow
Faculty of Health Data Science, Juntendo University（静冈大学健康数据科学学院）；The Institute of Collaborative Innovation, University of Macau（澳门大学协同创新研究所）；Department of Information and Computing Sciences, Faculty of Science, Utrecht University（乌得勒支大学科学学院信息与计算科学系）；Department of Computer and Information Science, University of Pennsylvania（宾夕法尼亚大学计算机与信息科学系）；School of Computer Science, University of Chinese Academy of Sciences（中国科学院大学计算机科学学院）；Department of Computer & Information Science & Engineering, University of Florida（佛罗里达大学计算机与信息科学与工程系）；Department of Computer Science, Juniata College（朱尼塔学院计算机科学系）；National Engineering Research Center for Beijing Biochip Technology（北京生物芯片工程技术研究中心）；CapitalBio Corporation（资本生物公司）；Faculty of Engineering & Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院）；University Research and Innovation Center (EKIK), Obuda University（布达佩斯大学研究与创新中心（EKIK））；Faculty of Science and Technology, University of Macau（澳门大学科学与技术学院）；Department of Mathematics, University of Southern California（南加州大学数学系）
Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement
The Hong Kong Polytechnic University（香港理工大学）；The Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）；Huazhong University of Science and Technology（华中科技大学）
Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造研究院）；University of Chinese Academy of Sciences（中国科学院大学）；College of Automation Science and Engineering, South China University of Technology（华南理工大学自动化科学与工程学院）；Peking University（北京大学）
Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay
School of Computer Science and Engineering, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Southeast University（东南大学计算机科学与工程学院、教育部新一代人工智能技术及其跨学科应用重点实验室）；School of Cyber Science and Engineering, Engineering Research Center of Blockchain Application, Supervision And Management (Southeast University), Ministry of Education, Southeast University（东南大学网络空间安全学院、教育部区块链应用监管工程研究中心（东南大学））；New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所模式识别国家重点实验室、多模态人工智能系统全国重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Organizing Background to Explore Latent Classes for Incremental Few-shot Semantic Segmentation
University of Chinese Academy of Sciences（中国科学院大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
Efficient Non-Exemplar Class-Incremental Learning with Retrospective Feature Synthesis
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；School of Optics and Photonics, Beijing Institute of Technology（北京理工大学光电学院）；School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）
EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
Communication Center (MICC), University of Florence, Italy Tomaso Trinci. ORCID: 0000-0002-4052-1930 Global Optimization Laboratory, University of Florence, Italy Albin Soutif - Cormerais. ORCID: 0009-0008-1564-2029 LAMP Team, Computer Vision Center, Barcelona, Spain Joost van de Weijer. ORCID: 0000-0002-9656-9706 LAMP Team, Computer Vision Center, Universitat Aut\` o noma de Barcelona, Spain Andrew D. Bagdanov. ORCID: 0000-0001-6408-7043 Media Integration；Communication Center (MICC), University of Florence, Italy Equal contribution
MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning
School of Computer Science and Information Security（计算机科学与信息安全学院）；School of Artificial Intelligence（人工智能学院）；School of Internet of Things Engineering（物联网工程学院）
Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning. Compared to standard object detection, the OWOD setting is task to: 1) detect objects seen during training while identifying unseen classes, and 2) incrementally learn the knowledge of the identified unknown objects when the corresponding annotations is available. We propose a novel and efficient OWOD solution from a prototype perspective, which we call OCPL: Open-world object detection via discriminative Class Prototype Learning, which consists of a Propo…
SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation
University of Surrey, UK（英国萨里大学）；University of Wollongong, Australia（澳大利亚沃拉彭大学）；University of Copenhagen, Denmark（丹麦哥本哈根大学）；University of Exeter, UK（英国埃克塞特大学）；Singapore University of Technology and Design, Singapore（新加坡科技与设计大学）
Peking University（北京大学）；University of Oxford（牛津大学）；JD Explore Academy（京东探索研究院）；Wuhan University（武汉大学）；Peng Cheng Laboratory（鹏城实验室）
Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the backbone or adjusting the classifier prototypes trained in the prior sessions would inevitably cause a misalignment between the feature and classifier of old classes, which explains the well-known catastrophic forgetting problem. In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same clas…
Brain-inspired analogical mixture prototypes for few-shot class-incremental learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院）
IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learning
College of Intelligent Robotics and Advanced Manufacturing, Fudan University（智能机器人与先进制造学院，复旦大学）；School of Microelectronics, Fudan University（微电子学院，复旦大学）；Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology（教育部先进化工过程控制与优化重点实验室，东华大学）
Towards Non-Exemplar Semi-Supervised Class-Incremental Learning
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）
Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification
South China University of Technology（南方科技大学）；State Key Laboratory of Subtropical Building Science（亚热带建筑科学国家重点实验室）；Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information（广东省计算智能与网络信息重点实验室）；Ministry of Education Key Laboratory of Big Data and Intelligent Robot（教育部大数据与智能机器人重点实验室）；Singapore Management University（新加坡国立大学）
Incremental learning is a form of online learning. Incremental learning can modify the parameters and structure of the deep learning model so that the model does not forget the old knowledge while learning new knowledge. Preventing catastrophic forgetting is the most important task of incremental learning. However, the current incremental learning is often only for one type of input. For example, if the input images are of the same type, the current incremental model can learn new knowledge while not forgetting old knowledge. However, if several categories are added to the input graphics, the …
Chinese Academy of Science（中国科学院）；Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；Xi’an Jiaotong University（西安交通大学）；Jinan University（暨南大学）
Although data-free incremental learning methods are memory-friendly, accurately estimating and counteracting representation shifts is challenging in the absence of historical data. This paper addresses this thorny problem by proposing a novel incremental learning method inspired by human analogy capabilities. Specifically, we design an analogy-making mechanism to remap the new data into the old class by prompt tuning. It mimics the feature distribution of the target old class on the old model using only samples of new classes. The learnt prompts are further used to estimate and counteract the …
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data set containing disjoint yet related categories. Apart from discovering novel classes, we also aim at preserving the ability of the model to recognize previously seen base categories. Inspired by rehearsal-based incremental learning methods, in this paper we propose a novel approach for class-iNCD which prevents forgetting of past information about the base c…
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；University of Rochester（罗切斯特大学）
Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved. It is a challenging task since representation optimization and feature retention can only be achieved under supervision from new classes. To address this problem, we propose a novel self-sustaining representation expansion scheme. Our scheme consists of a structure reorganization strategy that fuses main-branch expansion and side-branch updating to maintain the old features, and a main-branch distillation scheme to transfer the invariant knowledge. Furthermore, a prototy…
Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning
HUST AI & Visual Learning Lab (HAIV Lab)（华中科技大学人工智能与视觉学习实验室）；Huazhong University of Science and Technology (HUST)（华中科技大学）；Department of Computer Science（计算机科学系）；Boston University（波士顿大学）；ByteDance, Inc.（字节跳动公司）
PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning
Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）；Institute of Automation of Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors
School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；Data61, CSIRO（CSIRO数据61研究中心）；School of Computer Science, University of Auckland（奥克兰大学计算机科学学院）；Australian Institute for Machine Learning (AIML), The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）
