Enhanced Spectral Clustering Robust Aggregation for Lens Detection in Federated Learning Against Byzantine Attacks [0.03%]
用于联合学习对抗拜占庭攻击的镜头检测增强光谱聚类稳健聚合方法
Fenhua Bai,Bangming Jin,Kai Zeng et al.
Fenhua Bai et al.
Although federated learning (FL) addresses the issues of centralized data storage and privacy leakage, its distributed nature makes it vulnerable to malicious clients. These malicious participants introduce malicious parameters during the t...
Compressed Sensing via Sequential Majorization-Minimization and Collaborative Neurodynamic Optimization [0.03%]
基于序列重大化-极小化与协作神经动力学优化的压缩感知
Hongzong Li,Jun Wang,Hangjun Che et al.
Hongzong Li et al.
Compressed sensing formulations that target an $/ell _{0}$ -norm objective are inherently nonconvex and discontinuous. In this article, a global optimization problem with a power-mean function is first formulated for compressed sensing. To ...
Deep Semi-Supervised Learning via Tensor Label Propagation for High-Dimension-Low-Sample-Size Data [0.03%]
基于张量标签传播的深度半监督学习方法及其在高维低样本数据上的应用研究
Hongmin Cai,Jiali Sun,Fei Qi et al.
Hongmin Cai et al.
Semi-supervised learning (SSL) aims to effectively utilize a small amount of labeled data together with a large volume of unlabeled data to improve learning performance. Among various SSL strategies, label propagation has been widely adopte...
Beyond Euclidean Tokens: Hyperbolic Structure-Aware Mapping for Dual-Task Scene Parsing With Only Minimal Trainable Parameters [0.03%]
超越欧式令牌：具有最小可训练参数的双任务场景解析的双曲结构感知映射
Jiawei Liu,Da Yang,Tingwei Feng
Jiawei Liu
Achieving unified scene parsing that simultaneously outputs cross-domain semantic segmentation and depth estimation without scene-specific retraining is crucial for robust perception in complex real-world environments, yet remains a challen...
Gong Gao,Weidong Zhao,Xianhui Liu et al.
Gong Gao et al.
Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations. However, most existing BPRL...
Ukjo Hwang,Songnam Hong
Ukjo Hwang
Robust reinforcement learning (RRL) aims to develop a robust policy that maintains stable performance across diverse environments characterized by an uncertainty set. This set consists of perturbed environments derived from a nominal (train...
TAF-Net: Temporal-Adaptive Fusion Framework for Semisupervised Segmentation of Intracranial Arteries in DSA Sequences [0.03%]
基于DSA序列的颅内动脉半监督分割的时序自适应融合框架(TAF-Net)
Yuanjing Wang,Yuhan Xie,Shuyu Chang et al.
Yuanjing Wang et al.
Accurate segmentation of intracranial arteries in digital subtraction angiography (DSA) sequences is critical for cerebrovascular diagnosis but remains challenging due to limited annotations and complex vascular structures. We propose the t...
Yang-Jun Deng,Wenhao Deng,Longfei Ren et al.
Yang-Jun Deng et al.
Although existing bipartite graph-based multiview clustering (MVC) methods effectively exploit the structural relationships within multiview data, they exhibit three major limitations: 1) they primarily focus on direct similarities between ...
Minimizing Time Derivative of Loss for Efficient Generalization Enhancement With Applications to Nickel-Cobalt Alloy Defect Detection [0.03%]
损失时间导数最小化：高效泛化增强的理论与应用——镍钴合金缺陷检测案例研究
Qihai Jiang,Liangming Chen,Dalin Chen et al.
Qihai Jiang et al.
Deep neural networks (DNNs) achieve impressive performance, yet their effectiveness in complex and real-world settings remains limited by insufficient generalization. Recent studies analyze the geometry of the loss landscape, particularly i...
Dong Huang,Sheng-Yu Liu,Haiyan Wang
Dong Huang
Multi-view clustering (MVC) has attracted significant attention in recent years due to its ability to leverage heterogeneous features from multiple views. However, existing methods often lack the ability to jointly model first-order and top...