Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Mo, Zitao"'
Autor:
Zhu, Zeyu, Li, Fanrong, Li, Gang, Liu, Zejian, Mo, Zitao, Hu, Qinghao, Liang, Xiaoyao, Cheng, Jian
Graph Neural Networks (GNNs) are becoming a promising technique in various domains due to their excellent capabilities in modeling non-Euclidean data. Although a spectrum of accelerators has been proposed to accelerate the inference of GNNs, our anal
Externí odkaz:
http://arxiv.org/abs/2311.09775
Autor:
Yao, Xingting, Hu, Qinghao, Zhou, Fei, Liu, Tielong, Mo, Zitao, Zhu, Zeyu, Zhuge, Zhengyang, Cheng, Jian
In this paper, we propose SpikingNeRF, which aligns the temporal dimension of spiking neural networks (SNNs) with the radiance rays, to seamlessly accommodate SNNs to the reconstruction of neural radiance fields (NeRF). Thus, the computation turns in
Externí odkaz:
http://arxiv.org/abs/2309.10987
Autor:
Zhu, Zeyu, Li, Fanrong, Mo, Zitao, Hu, Qinghao, Li, Gang, Liu, Zejian, Liang, Xiaoyao, Cheng, Jian
As graph data size increases, the vast latency and memory consumption during inference pose a significant challenge to the real-world deployment of Graph Neural Networks (GNNs). While quantization is a powerful approach to reducing GNNs complexity, m
Externí odkaz:
http://arxiv.org/abs/2302.00193
Spiking Neural Networks (SNNs) have been studied over decades to incorporate their biological plausibility and leverage their promising energy efficiency. Throughout existing SNNs, the leaky integrate-and-fire (LIF) model is commonly adopted to formu
Externí odkaz:
http://arxiv.org/abs/2210.13768
Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond these semantic metrics, this paper aims to introduce location supervision into semantic segmen
Externí odkaz:
http://arxiv.org/abs/1911.05250
Autor:
Li, Fanrong, Mo, Zitao, Wang, Peisong, Liu, Zejian, Zhang, Jiayun, Li, Gang, Hu, Qinghao, He, Xiangyu, Leng, Cong, Zhang, Yang, Cheng, Jian
Object detection has made impressive progress in recent years with the help of deep learning. However, state-of-the-art algorithms are both computation and memory intensive. Though many lightweight networks are developed for a trade-off between accur
Externí odkaz:
http://arxiv.org/abs/1909.10964
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.