Pontificia Universidad Católica de Chile(智利天主教大学);King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学);University of Pisa(比萨大学);Adobe Research(Adobe研究院)
Andrés Villa, Juan León Alcázar, Motasem Alfarra, Kumail Alhamoud, Julio Hurtado, Fabian Caba Heilbron, Alvaro Soto, Bernard Ghanem
Modern machine learning pipelines are limited due to data availability, storage quotas, privacy regulations, and expensive annotation processes. These constraints make it difficult or impossible to train and update large-scale models on such dynamic annotated sets. Continual learning directly approaches this problem, with the ultimate goal of devising methods where a deep neural network effectively learns relevant patterns for new (unseen) classes, without significantly altering its performance on previously learned ones. In this paper, we address the problem of continual learning for video data. We introduce PIVOT, a novel method that leverages extensive knowledge in pre-trained models from the image domain, thereby reducing the number of trainable parameters and the associated forgetting. Unlike previous methods, ours is the first approach that effectively uses prompting mechanisms for continual learning without any in-domain pre-training. Our experiments show that PIVOT improves state-of-the-art methods by a significant 27% on the 20-task ActivityNet setup.
Consistent Prompting for Rehearsal-Free Continual Learning
School of Artificial Intelligence, Sun Yat-sen University(中山大学人工智能学院);Cheng Kar-Shun Robotics Institute, The Hong Kong University of Science and Technology(香港科技大学郑家纯机器人研究院);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education(教育部机器智能与先进计算重点实验室)
Adapter-Enhanced Semantic Prompting for Continual Learning
Beijing Key Laboratory of Multimedia and Intelligent Software Technology(北京多媒体与智能软件技术重点实验室);Faculty of Information Technology, Beijing University of Technology(信息科技学院,北京理工大学);University of California at Merced(加州大学默塞德分校);Macquarie University(麦考瑞大学)
Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
The University of Texas at Dallas(德克萨斯大学达拉斯分校);LIVIA ETS Montreal, ILLS International Laboratory on Learning Systems (ILLS)(蒙特利尔LIVIA ETS,学习系统国际实验室(ILLS));Tulane University(路易斯安那州立大学);Nanyang Technological University(南洋理工大学);Hanyang University(翰阳大学)
Pengcheng laboratory(鹏城实验室);Harbin Institute of Technology(哈尔滨工业大学);Xi’an Jiaotong University(西安交通大学);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
PrePrompt: Predictive prompting for class incremental learning
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Department of Mathematics and Statistics, Beijing Technology and Business University(北京科技商务大学数学与统计学系);College of Science, Shantou University(汕头大学科学学院)
CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation
State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences(机器人与智能系统国家重点实验室,沈阳自动化研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning
Department of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术系);Research Center for Frontier Fundamental Studies, Zhejiang Lab(浙江实验室前沿基础研究中心);Department of Neurology, University of California, Irvine(加州大学伊市医学院神经科)