18 citations · 37 across the 6 of their papers we have counts for
6 papers
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…
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…
Teacher-Student Architecture for Knowledge Learning: A Survey
Chengming Hu, Xuan Li, Dan Liu +3
Although Deep Neural Networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs with voluminous parameters are hard to be deployed in a rea…
Confidence-Guided Unsupervised Domain Adaptation for Cerebellum Segmentation
Xuan Li, Paule-J Toussaint, Alan Evans +1
The lack of a comprehensive high-resolution atlas of the cerebellum has hampered studies of cerebellar involvement in normal brain function and disease. A good representation of th…
Out-of-Distribution Detection for Skin Lesion Images with Deep Isolation Forest
Xuan Li, Yuchen Lu, Christian Desrosiers +1
In this paper, we study the problem of out-of-distribution detection in skin disease images. Publicly available medical datasets normally have a limited number of lesion classes (e…
Boosting Image Recognition with Non-differentiable Constraints
Xuan Li, Yuchen Lu, Peng Xu +3
In this paper, we study the problem of image recognition with non-differentiable constraints. A lot of real-life recognition applications require a rich output structure with deter…