Výsledky vyhledávání - "Xia, Yizhang"

Report

An Evolutionary Network Architecture Search Framework with Adaptive Multimodal Fusion for Hand Gesture Recognition

Autor: Xia, Yizhang, Song, Shihao, Hou, Zhanglu, Xu, Junwen, Zou, Juan, Liu, Yuan, Yang, Shengxiang

Hand gesture recognition (HGR) based on multimodal data has attracted considerable attention owing to its great potential in applications. Various manually designed multimodal deep networks have performed well in multimodal HGR (MHGR), but most of ex

Externí odkaz: http://arxiv.org/abs/2403.18208

Zobrazit plný text záznamu

Report

Multiple Population Alternate Evolution Neural Architecture Search

Autor: Zou, Juan, Chu, Han, Xia, Yizhang, Xu, Junwen, Liu, Yuan, Hou, Zhanglu

The effectiveness of Evolutionary Neural Architecture Search (ENAS) is influenced by the design of the search space. Nevertheless, common methods including the global search space, scalable search space and hierarchical search space have certain limi

Externí odkaz: http://arxiv.org/abs/2403.07035

Zobrazit plný text záznamu

Report

G-EvoNAS: Evolutionary Neural Architecture Search Based on Network Growth

Autor: Zou, Juan, Jiang, Weiwei, Xia, Yizhang, Liu, Yuan, Hou, Zhanglu

The evolutionary paradigm has been successfully applied to neural network search(NAS) in recent years. Due to the vast search complexity of the global space, current research mainly seeks to repeatedly stack partial architectures to build the entire

Externí odkaz: http://arxiv.org/abs/2403.02667

Zobrazit plný text záznamu

Report

Combining Kernelized Autoencoding and Centroid Prediction for Dynamic Multi-objective Optimization

Autor: Hou, Zhanglu, Zou, Juan, Ruan, Gan, Liu, Yuan, Xia, Yizhang

Evolutionary algorithms face significant challenges when dealing with dynamic multi-objective optimization because Pareto optimal solutions and/or Pareto optimal fronts change. This paper proposes a unified paradigm, which combines the kernelized aut

Externí odkaz: http://arxiv.org/abs/2312.00978

Zobrazit plný text záznamu

Report

TS-ENAS:Two-Stage Evolution for Cell-based Network Architecture Search

Autor: Zou, Juan, Wu, Shenghong, Xia, Yizhang, Jiang, Weiwei, Wu, Zeping, Zheng, Jinhua

Neural network architecture search provides a solution to the automatic design of network structures. However, it is difficult to search the whole network architecture directly. Although using stacked cells to search neural network architectures is a

Externí odkaz: http://arxiv.org/abs/2310.09525

Zobrazit plný text záznamu