Výsledky vyhledávání - "Yang, Kunshan"

Report

Toward End-to-End Bearing Fault Diagnosis for Industrial Scenarios with Spiking Neural Networks

Autor: Ding, Yongqi, Zuo, Lin, Jing, Mengmeng, Yang, Kunshan, Chen, Biao, Yu, Yunqian

Spiking neural networks (SNNs) transmit information via low-power binary spikes and have received widespread attention in areas such as computer vision and reinforcement learning. However, there have been very few explorations of SNNs in more practic

Externí odkaz: http://arxiv.org/abs/2408.11067

Zobrazit plný text záznamu

Report

Temporal Reversed Training for Spiking Neural Networks with Generalized Spatio-Temporal Representation

Autor: Zuo, Lin, Ding, Yongqi, Luo, Wenwei, Jing, Mengmeng, Tian, Xianlong, Yang, Kunshan

Spiking neural networks (SNNs) have received widespread attention as an ultra-low energy computing paradigm. Recent studies have focused on improving the feature extraction capability of SNNs, but they suffer from inefficient inference and suboptimal

Externí odkaz: http://arxiv.org/abs/2408.09108

Zobrazit plný text záznamu

Report

Self-Distillation Learning Based on Temporal-Spatial Consistency for Spiking Neural Networks

Autor: Zuo, Lin, Ding, Yongqi, Jing, Mengmeng, Yang, Kunshan, Yu, Yunqian

Spiking neural networks (SNNs) have attracted considerable attention for their event-driven, low-power characteristics and high biological interpretability. Inspired by knowledge distillation (KD), recent research has improved the performance of the

Externí odkaz: http://arxiv.org/abs/2406.07862

Zobrazit plný text záznamu

Report

Flexible ViG: Learning the Self-Saliency for Flexible Object Recognition

Autor: Zuo, Lin, Yang, Kunshan, Tian, Xianlong, He, Kunbin, Ding, Yongqi, Jing, Mengmeng

Existing computer vision methods mainly focus on the recognition of rigid objects, whereas the recognition of flexible objects remains unexplored. Recognizing flexible objects poses significant challenges due to their inherently diverse shapes and si

Externí odkaz: http://arxiv.org/abs/2406.18585

Zobrazit plný text záznamu