Han Liu,Zhiliang Hao,Haoliang Ming et al.
Han Liu et al.
Graph long-tailed learning has garnered significant research attention. However, prevailing works in this domain typically assume the cleanliness of training dataset labels, neglecting the reality of noisy labels in real-world data. Such ch...
An Uncertainty-Aware Ensemble Approach to Modeling Utility of Pseudolabels for Semisupervised Learning [0.03%]
一种不确定性感知的集成方法，用于建模半监督学习中伪标签的效用
Jiaqi Wu,Junbiao Pang,Qingming Huang
Jiaqi Wu
Semisupervised learning (SSL) typically filters out low-confidence predictions when generating pseudolabels. This paradigm suffers from two critical limitations: 1) the lack of an effective strategy for determining a confidence threshold an...
Spatiotemporal Context-Aware Prompting With Low-Rank Dynamic Routing for Exemplar-Free Video Class-Incremental Learning [0.03%]
基于低秩动态路由的时空上下文感知提示的无示例视频类别渐进学习方法
Kunlun Wu,Bo Peng,Donghai Zhai
Kunlun Wu
Video class-incremental learning (VCIL) aims to progressively recognize novel action categories while preserving spatial-temporal knowledge of previous tasks. Unlike image class-incremental learning (CIL), VCIL requires simultaneously captu...
Structure-Guided Domain-Adaptive Network for Few-Shot SAR Ship Detection [0.03%]
基于结构引导的领域适应网络的少样本SAR船舶检测方法
Kang Ni,Weihang Zhou
Kang Ni
Due to the complexity of synthetic aperture radar (SAR) imaging mechanisms, SAR ship detection faces challenges such as difficulty in sample annotation and the influence of complex backgrounds, leading to poor target readability and difficu...
Interpreting the Observed Behavior of a Class of Autonomous Linear Systems Using Explainable Inverse Reinforcement Learning [0.03%]
基于可解释的逆强化学习的自主线性系统的观测行为解读
Adolfo Perrusquia,Mengbang Zou,Weisi Guo
Adolfo Perrusquia
One of the main challenges faced by society is how to verify the safety of autonomous systems. As the level of autonomy grows, it becomes critical to understand why an autonomous system exhibits a particular behavior and what we need to do ...
Flexible Prescribed-Time Optimal Control With Adaptive State-Input Constraint Bounds via Actor-Critic Learning [0.03%]
基于演员评论家学习的自适应状态输入约束边界的灵活规定时间最优控制
Junkai Tan,Shuangsi Xue,Hui Cao et al.
Junkai Tan et al.
This article develops a prescribed-time (PT) optimal tracking framework for nonlinear systems with concurrent state and input constraints. The main focus is a flexible PT constraint-handling mechanism that is introduced first in the design:...
Roya Aliakbarisani,Robert Jankowski,M Angeles Serrano et al.
Roya Aliakbarisani et al.
Graph neural networks (GNNs) have excelled in predicting graph properties in various applications ranging from identifying trends in social networks to drug discovery and malware detection. With the abundance of new architectures and increa...
Huihui Zhang,Guoyin Chen
Huihui Zhang
Traditional online reinforcement learning (RL) systems operate by actively engaging with their environments to acquire data, with the goal of formulating an optimal policy that maximizes a predefined cumulative reward. However, in scenarios...
Jibin Peng,Haotian Dong,Xin Wang et al.
Jibin Peng et al.
Visual context is essential for point cloud semantic segmentation. The contextual information captures the semantic relationship between 3-D points, providing helpful hints for reasoning the category labels of points. Most current methods h...
An Accelerated Augmented Gradient Neural Network for Constrained Time-Varying Nonlinear Optimization [0.03%]
求解约束非线性时变优化问题的加速增广梯度神经网络
Juliang Wang,Haoen Huang,Kun Deng et al.
Juliang Wang et al.
The constrained time-varying nonlinear optimization (CTVNO) problems with the linear equality and inequality constraints have attracted increasing attention in recent years. Although some models have been developed to address these problems...