Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond
Dalian University of Technology(大连理工大学);Southern University of Science and Technology(南方科技大学);Xi’an Jiaotong University(西安交通大学);Peking University(北京大学);Shanghai Jiao Tong University(上海交通大学)
Risheng Liu, Jiaxin Gao, Jin Zhang, Deyu Meng, Zhouchen Lin
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta-learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research.
Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models
Beijing Key Lab of Traffic Data Analysis and Mining(北京交通数据挖掘重点实验室);Beijing Jiaotong University(北京交通大学);Unisound AI Technology Co., Ltd.(Unisound人工智能技术有限公司);Peng Cheng Lab(鹏城实验室)
Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective
Fraunhofer Institute for Applied Information Technology FIT, Germany(弗劳恩霍夫应用信息科技研究所);Soochow University, China(苏州大学);University Hospital of Cologne, Germany(科隆大学医院)
Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors
Intelligent Autonomous Systems Lab, Department of Computer Science, TU Darmstadt, Germany(图腾达姆斯塔特大学计算机科学系智能自主系统实验室);German Research Center for AI (DFKI)(德国人工智能研究中心);Department of Psychology, University of Giessen, Germany(吉森大学心理学系);Centre for Cognitive Science, TU Darmstadt(图腾达姆斯塔特大学认知科学中心);Hessian Center for Artificial Intelligence (Hessian.AI), Darmstadt(黑森人工智能中心(Hessian.AI),达姆斯塔特)
Investigating the Robustness of Vision Transformers against Label Noise in Medical Image Classification
Center for Imaging Science, Rochester Institute of Technology(罗切斯特理工大学成像科学中心);NepAl Applied Mathematics and Informatics Institute for Research (NAAMII)(尼泊尔应用数学与信息学研究所);University of Aberdeen(阿伯丁大学);Biomedical Engineering, Rochester Institute of Technology(罗切斯特理工大学生物医学工程系)
Investigating the Impact of Balancing, Filtering, and Complexity on Predictive Multiplicity: A Data-Centric Perspective
Eskisehir Technical University, Department of Statistics(埃斯克谢希大学统计系);Warsaw University of Technology, Faculty of Mathematics and Information Science(华沙技术大学数学与信息科学学院);University of Warsaw, Faculty of Mathematics, Informatics and Mechanics(华沙大学数学、信息学与力学学院)
A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective
The University of Hong Kong(香港大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Future Network of Intelligence Institute, CUHK-Shenzhen(香港中文大学(深圳)未来智联网络研究院);ShanghaiTech University(上海科技大学)
Enhancing Data Space Semantic Interoperability through Machine Learning: a Visionary Perspective
Fraunhofer Institute for Applied Information Technology FIT(弗劳恩霍夫应用信息技术研究所(FIT));University Hospital Cologne(科隆大学医院);RWTH Aachen University(亚琛工业大学);University of Cologne(科隆大学)