1 code implementation • 3 Mar 2024 • Xin Zhou, Dingkang Liang, Wei Xu, Xingkui Zhu, Yihan Xu, Zhikang Zou, Xiang Bai
To achieve this goal, we freeze the parameters of the default pre-trained models and then propose the Dynamic Adapter, which generates a dynamic scale for each token, considering the token significance to the downstream task.
1 code implementation • 16 Feb 2024 • Dingkang Liang, Xin Zhou, Xinyu Wang, Xingkui Zhu, Wei Xu, Zhikang Zou, Xiaoqing Ye, Xiang Bai
Recently, state space models (SSM), a new family of deep sequence models, have presented great potential for sequence modeling in NLP tasks.
1 code implementation • 21 Aug 2023 • Wenwen Yu, Yuliang Liu, Xingkui Zhu, Haoyu Cao, Xing Sun, Xiang Bai
Utilizing only 10% of the supervised data, FastTCM-CR50 improves performance by an average of 26. 5% and 5. 5% for text detection and spotting tasks, respectively.
2 code implementations • 26 Aug 2021 • Xingkui Zhu, Shuchang Lyu, Xu Wang, Qi Zhao
Object detection on drone-captured scenarios is a recent popular task.