no code implementations • 22 Dec 2023 • Chengming Hu, Haolun Wu, Xuan Li, Chen Ma, Xi Chen, Jun Yan, Boyu Wang, Xue Liu
A simple neural network then learns the implicit mapping from the intra- and inter-sample relations to an adaptive, sample-wise knowledge fusion ratio in a bilevel-optimization manner.
no code implementations • 8 Aug 2023 • Chengming Hu, Xuan Li, Dan Liu, Haolun Wu, Xi Chen, Ju Wang, Xue Liu
Recently, Teacher-Student architectures have been effectively and widely embraced on various knowledge distillation (KD) objectives, including knowledge compression, knowledge expansion, knowledge adaptation, and knowledge enhancement.
no code implementations • 24 Jul 2023 • Chengming Hu, Yeqian Du, Rui Wang, Hao Chen
In this paper, we aim to clarify the relationships between Domain Generalization (DG) and the frequency components, and explore the spatial relationships of the phase spectrum.
no code implementations • 28 Oct 2022 • Chengming Hu, Xuan Li, Dan Liu, Xi Chen, Ju Wang, Xue Liu
To tackle this issue, Teacher-Student architectures were first utilized in knowledge distillation, where simple student networks can achieve comparable performance to deep teacher networks.
no code implementations • 20 Mar 2022 • Yuecai Zhu, Fuyuan Lyu, Chengming Hu, Xi Chen, Xue Liu
However, the temporal information embedded in the dynamic graphs brings new challenges in analyzing and deploying them.
no code implementations • 29 Sep 2021 • Jikun Kang, Xi Chen, Ju Wang, Chengming Hu, Xue Liu, Gregory Dudek
Results show that, compared with SOTA model-free methods, our method can improve the data efficiency and system performance by up to 75% and 10%, respectively.