1 code implementation • 12 Mar 2024 • Feilong Tang, Zhongxing Xu, Zhaojun Qu, Wei Feng, Xingjian Jiang, ZongYuan Ge
Inspired by prototype learning theory, we propose leveraging prototype awareness to capture diverse and fine-grained feature attributes of instances.
1 code implementation • 22 Jan 2024 • Xinqiao Zhao, Feilong Tang, Xiaoyang Wang, Jimin Xiao
Specifically, we leverage the class prototypes that carry positive shared features and propose a Multi-Scaled Distribution-Weighted (MSDW) consistency loss for narrowing the gap between the CAMs generated through classifier weights and class prototypes during training.
no code implementations • 26 Sep 2023 • Haobing Liu, Jianyu Ding, Yanmin Zhu, Feilong Tang, Jiadi Yu, Ruobing Jiang, Zhongwen Guo
To extract multi-aspect preferences from target behaviors, we propose a multi-aspect projection mechanism for generating multiple preference representations from multiple aspects.
1 code implementation • 21 Dec 2022 • Feilong Tang, Qiming Huang, Jinfeng Wang, Xianxu Hou, Jionglong Su, Jingxin Liu
The GLSA has the ability to aggregate and represent both global and local spatial features, which are beneficial for locating large and small objects, respectively.
Ranked #1 on Medical Image Segmentation on 2018 Data Science Bowl
no code implementations • 24 Jul 2022 • Haobing Liu, Yanmin Zhu, Chunyang Wang, Jianyu Ding, Jiadi Yu, Feilong Tang
An unsupervised way to construct a social behavior graph based on spatio-temporal data and to model social influences is proposed.
no code implementations • 9 Jun 2022 • Chunyang Wang, Yanmin Zhu, Haobing Liu, Tianzi Zang, Jiadi Yu, Feilong Tang
For each recommendation scenario, we further discuss technical details about how existing methods apply meta-learning to improve the generalization ability of recommendation models.
1 code implementation • 7 Mar 2022 • Jinfeng Wang, Qiming Huang, Feilong Tang, Jia Meng, Jionglong Su, Sifan Song
However, due to the structure of polyps image and the varying shapes of polyps, it easy for existing deep learning models to overfitting the current dataset.
Ranked #2 on Medical Image Segmentation on 2018 Data Science Bowl
no code implementations • 25 Mar 2021 • Haobing Liu, Yanmin Zhu, Tianzi Zang, Yanan Xu, Jiadi Yu, Feilong Tang
In this paper, we focus on modeling heterogeneous behaviors and making multiple predictions together, since some prediction tasks are related and learning the model for a specific task may have the data sparsity problem.