19 citations · 63 across the 15 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.LG2023★ 2 cited
Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
Chengming Hu, Haolun Wu, Xuan Li +5
Knowledge distillation aims to train a compact student network using soft supervision from a larger teacher network and hard supervision from ground truths. However, determining an…
cs.LG2023★ 13 cited
Teacher-Student Architecture for Knowledge Distillation: A Survey
Chengming Hu, Xuan Li, Dan Liu +4
Although Deep neural networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs are hard to be deployed in real-world systems due to their…
cs.CV2023★ 1 cited
Phase Matching for Out-of-Distribution Generalization
Chengming Hu, Yeqian Du, Rui Wang +2
The Fourier transform, an explicit decomposition method for visual signals, has been employed to explain the out-of-distribution generalization behaviors of Deep Neural Networks (D…