Despite continual learning's long and well-established academic history, its application in real-world scenarios remains rather limited. This paper contends that this gap is attributable to a misalignment between the actual challenges of continual learning and the evaluation protocols in use, rendering proposed solutions ineffective for addressing the complexities of real-world setups. We validate our hypothesis and assess progress to date, using a new 3D semantic segmentation benchmark, OCL-3DSS. We investigate various continual learning schemes from the literature by utilizing more realistic protocols that necessitate online and continual learning for dynamic, real-world scenarios (eg., in robotics and 3D vision applications). The outcomes are sobering: all considered methods perform poorly, significantly deviating from the upper bound of joint offline training. This raises questions about the applicability of existing methods in realistic settings. Our paper aims to initiate a paradigm shift, advocating for the adoption of continual learning methods through new experimental protocols that better emulate real-world conditions to facilitate breakthroughs in the field.
Towards Field-Ready AI-based Malaria Diagnosis: A Continual Learning Approach
institutetext: MyC, Paris, France(MyC);institutetext: CHU Campus, Ministère de la Santé et de l’hygiène Publique, Lomé, Togo(CHU Campus);institutetext: Service de Parasitologie-Mycologie, Hôpital de La Pitié-Salpêtrière, Assistance Publique-Hôpitaux de Paris (AP-HP), France(Service de Parasitologie-Mycologie);institutetext: CHU of Montpellier, Université de Montpellier, Montpellier, France(CHU of Montpellier);institutetext: PNLP Togo, Lomé, Togo(PNLP Togo);institutetext: CHU Sylvanus Olympio, Lomé, Togo(CHU Sylvanus Olympio);institutetext: Institut Pierre-Louis d’Epidémiologie et de Santé Publique, INSERM, Sorbonne Université, Paris, France(Institut Pierre-Louis d’Epidémiologie et de Santé Publique);institutetext: Faculté des Sciences de la Santé, Université de Lomé, Lomé, Togo(Faculté des Sciences de la Santé)
Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning
Centre for Artificial Intelligence and Robotics(人工智能与机器人中心);Hong Kong Institute of Science and Innovation(香港科学与创新研究院);Chinese Academy of Sciences(中国科学院);Department of Computer Science(计算机科学系);City University of Hong Kong(香港城市大学);The Department of Neurosurgery(神经外科部门);Peking University First Hospital(北京大学第一医院);State Key Laboratory of Multimodal Artificial Intelligence Systems(多模态人工智能系统国家重点实验室);Institute of Automation(自动化研究所);Hong Kong SAR, China(香港特别行政区,中国)
Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks
Center of Data Science and Artificial Intelligence & School of Engineering and Computer Science(数据科学与人工智能中心及工程与计算机科学学院);Victoria University of Wellington(怀特维尔大学);School of Data Science(数据科学学院)
本文提出了一种应对持续漂移任务的终身学习方法,通过Dual Replay with Experience Enhancement框架提升学习效率并缓解灾难性遗忘。
Exploring Open-world Continual Learning with Knowns-Unknowns Knowledge Transfer
Southwestern University of Finance and Economics(西南财经大学);Leiden University(莱顿大学);School of Computing and Artificial Intelligence, Southwest Jiaotong University(西南交通大学计算机与人工智能学院)
Review learning: Real world validation of privacy preserving continual learning across medical institutions
organization= School of Electrical Engineering, Korea University;organization= Department of Biomedical Engineering, Seoul National University College of Medicine;organization= Department of Medicine, Seoul National University College of Medicine;organization= Department of Applied Statistics, Chung-Ang University;organization= Department of Cardiology, Cardiovascular Center, College of Medicine, Korea University;organization= Department of Endocrinology;Metabolism, School of Medicine, Ajou University;organization= Department of Biomedical Informatics, School of Medicine, Ajou University;organization= Transdisciplinary Department of Medicine \& Advanced Technology, Seoul National University Hospital
Improving Open-world Continual Learning under the Constraints of Scarce Labeled Data
Southwestern University of Finance and Economics(西南财经大学);Leiden University(莱顿大学);JD Intelligent Cities Research(京东智能城市研究院);Southwest Jiaotong University(西南交通大学)
本文研究开放世界少样本持续学习问题,提出集成 ITA、MOB 和 AKS 的 OFCL 框架,以缓解遗忘、过拟合、开放检测及未知向已知更新难题。
Where is the Truth? The Risk of Getting Confounded in a Continual World
Computer Science Department, TU Darmstadt, Germany.(图宾根大学计算机科学系);Hessian Center for AI (hessian.AI), Germany.(黑森人工智能中心);German Research Center for AI (DFKI), Germany(德国人工智能研究中心);TU Darmstadt, Centre for Cognitive Science, Germany.(图宾根大学认知科学中心);University of Bremen, Department of Mathematics(不莱梅大学数学系)
PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
School of Artificial Intelligence, Nanjing University(南京大学人工智能学院);National Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室)
Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised 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)
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure
School of Telecommunications Engineering, Xidian University(西安电子科技大学通信工程学院);School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);Hefei Comprehensive National Science Center(合肥综合性国家科学中心);University of New South Wales (UNSW)(新南威尔士大学);Shandong Normal University(山东师范大学)
Continual Hand-Eye Calibration for Open-world Robotic Manipulation
School 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);State Key Laboratory of Robotics, the Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences(中国科学院机器人研究所);University of Chinese Academy of Sciences(中国科学院大学)