no code implementations • 29 Feb 2024 • Jiahao Zhou, Chen Long, Yue Xie, Jialiang Wang, Boheng Li, Haiping Wang, Zhe Chen, Zhen Dong
Therefore, such a unique attribute can assist in exploring the potential for the multi-task model and even the foundation model without separate training methods.
no code implementations • 16 Sep 2022 • Jiahao Zhou, Boheng Li, Qingxiang Meng
When using constellation synergy to image large areas for reconnaissance, it is required to achieve the coverage capability requirements with minimal consumption of observation resources to obtain the most optimal constellation observation scheme.
1 code implementation • 9 Jul 2021 • Shaowu Chen, Jiahao Zhou, Weize Sun, Lei Huang
To overcome this problem, we propose to compress CNNs and alleviate performance degradation via joint matrix decomposition, which is different from existing works that compressed layers separately.
Efficient Neural Network Matrix Factorization / Decomposition +1