no code implementations • 17 Oct 2019 • Xinxin Zhu, Longteng Guo, Peng Yao, Shichen Lu, Wei Liu, Jing Liu
This report describes our solution for the VATEX Captioning Challenge 2020, which requires generating descriptions for the videos in both English and Chinese languages.
no code implementations • CVPR 2020 • Longteng Guo, Jing Liu, Xinxin Zhu, Peng Yao, Shichen Lu, Hanqing Lu
First, we propose Normalized Self-Attention (NSA), a reparameterization of SA that brings the benefits of normalization inside SA.
no code implementations • 7 Jan 2021 • Shuwei Shen, Mengjuan Xu, Fan Zhang, Pengfei Shao, Honghong Liu, Liang Xu, Chi Zhang, Peng Liu, Zhihong Zhang, Peng Yao, Ronald X. Xu
At the network search stage, the DCNNs are fine-tuned with the full training set in order to select the model with the highest BACC.
1 code implementation • 2 Feb 2021 • Peng Yao, Shuwei Shen, Mengjuan Xu, Peng Liu, Fan Zhang, Jinyu Xing, Pengfei Shao, Benjamin Kaffenberger, Ronald X. Xu
This paper proposes a novel single-model based strategy for classification of skin lesions on small and imbalanced datasets.
no code implementations • 28 Jul 2021 • Fan Zhang, Bo Pan, Pengfei Shao, Peng Liu, Shuwei Shen, Peng Yao, Ronald X. Xu
In this research, we propose a novel end-to-end deep learning approach for automated diagnosis of AD and localization of important brain regions related to the disease from sMRI data.
no code implementations • 20 Oct 2021 • Yu Shen, Yang Li, Jian Zheng, Wentao Zhang, Peng Yao, Jixiang Li, Sen yang, Ji Liu, Bin Cui
Designing neural architectures requires immense manual efforts.
no code implementations • 24 May 2022 • Liang Xu, Yi Cheng, Fan Zhang, Bingxuan Wu, Pengfei Shao, Peng Liu, Shuwei Shen, Peng Yao, Ronald X. Xu
This loss is effective in addressing quantity imbalances and outliers, while regulating the focus of attention on samples with varying classification difficulties.
1 code implementation • 27 Jul 2023 • Liang Xu, Mingxiao Chen, Yi Cheng, Pengfei Shao, Shuwei Shen, Peng Yao, Ronald X. Xu
The Cross Perceptron first captures the local correlations using multiple Multi-scale Cross Perceptron modules, facilitating the fusion of features across scales.
no code implementations • 30 Aug 2023 • Qingyuan Li, Yifan Zhang, Liang Li, Peng Yao, Bo Zhang, Xiangxiang Chu, Yerui Sun, Li Du, Yuchen Xie
In this study, we propose a novel W4A8 post-training quantization method for the available open-sourced LLMs, which combines the advantages of both two recipes.
no code implementations • 17 Oct 2023 • Huan Yuan, Chao Liao, Jianchao Tan, Peng Yao, Jiyuan Jia, Bin Chen, Chengru Song, Di Zhang
To alleviate two disadvantages of two categories of methods, we propose to unify the static compression and dynamic compression techniques jointly to obtain an input-adaptive compressed model, which can further better balance the total compression ratios and the model performances.
no code implementations • 17 Oct 2023 • Peng Yao, Chao Liao, Jiyuan Jia, Jianchao Tan, Bin Chen, Chengru Song, Di Zhang
Deep neural networks have gained great success due to the increasing amounts of data, and diverse effective neural network designs.