no code implementations • 9 Jun 2023 • Hai Lan, Xian Wei
Recently, message-passing Neural networks (MPNN) provide a promising tool for dealing with molecular graphs and have achieved remarkable success in facilitating the discovery and materials design with desired properties.
no code implementations • 27 Feb 2023 • Xihao Wang, JiaMing Lei, Hai Lan, Arafat Al-Jawari, Xian Wei
The dual-equivariance of our model can extract the equivariant features at both local and global levels, respectively.
no code implementations • 5 Jan 2022 • Guangyang Zhu, Jianfeng Zhang, Yuanzhi Feng, Hai Lan
Self-attention module shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning.
no code implementations • 27 Dec 2021 • Xian Wei, Bin Wang, Mingsong Chen, Ji Yuan, Hai Lan, Jiehuang Shi, Xuan Tang, Bo Jin, Guozhang Chen, Dongping Yang
To address these problems, a novel method, namely, Vision Reservoir computing (ViR), is proposed here for image classification, as a parallel to ViT.
no code implementations • 27 Dec 2021 • Xian Wei, Yanhui Huang, Yangyu Xu, Mingsong Chen, Hai Lan, Yuanxiang Li, Zhongfeng Wang, Xuan Tang
Learning deep models with both lightweight and robustness is necessary for these equipments.
1 code implementation • 10 Dec 2021 • Hai Lan, Xihao Wang, Xian Wei
With the development of the self-attention mechanism, the Transformer model has demonstrated its outstanding performance in the computer vision domain.
no code implementations • 5 Jan 2021 • Hai Lan, Zhifeng Bao, Yuwei Peng
A cost-based optimizer introduces a plan enumeration algorithm to find a (sub)plan, and then uses a cost model to obtain the cost of that plan, and selects the plan with the lowest cost.