2 citations · 2 across the 4 of their papers we have counts for
6 papers
Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation
Zhengyuan Xie, Haiquan Lu, Jia-wen Xiao +3
Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prio…
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
Haiquan Lu, Xiaotian Liu, Yefan Zhou +6
Recent studies on deep ensembles have identified the sharpness of the local minima of individual learners and the diversity of the ensemble members as key factors in improving test…
Delay-Doppler Alignment Modulation for Spatially Sparse Massive MIMO Communication
Haiquan Lu, Yong Zeng
Delay alignment modulation (DAM) is an emerging technique for achieving inter-symbol interference (ISI)-free wideband communications using spatial-delay processing, without relying…
Achievable Rate Region and Path-Based Beamforming for Multi-User Single-Carrier Delay Alignment Modulation
Xingwei Wang, Haiquan Lu, Yong Zeng +2
Delay alignment modulation (DAM) is a novel wideband transmission technique for mmWave massive MIMO systems, which exploits the high spatial resolution and multi-path sparsity to m…
Near-Field Modelling and Performance Analysis for Extremely Large-Scale IRS Communications
Chao Feng, Haiquan Lu, Yong Zeng +3
Intelligent reflecting surface (IRS) is an emerging technology for wireless communications, thanks to its powerful capability to engineer the radio environment. However, in practic…
Modular Extremely Large-Scale Array Communication: Near-Field Modelling and Performance Analysis
Xinrui Li, Haiquan Lu, Yong Zeng +2
This paper investigates wireless communications based on a new antenna array architecture, termed modular extremely large-scale array (XL-array), where an extremely large number of…