Summary of Sinkhorn Distance Minimization For Knowledge Distillation, by Xiao Cui et al.
Sinkhorn Distance Minimization for Knowledge Distillationby Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan…
Sinkhorn Distance Minimization for Knowledge Distillationby Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan…
m2mKD: Module-to-Module Knowledge Distillation for Modular Transformersby Ka Man Lo, Yiming Liang, Wenyu Du, Yuantao…
Practical Insights into Knowledge Distillation for Pre-Trained Modelsby Norah Alballa, Marco CaniniFirst submitted to arxiv…
Wisdom of Committee: Distilling from Foundation Model to Specialized Application Modelby Zichang Liu, Qingyun Liu,…
On the Byzantine-Resilience of Distillation-Based Federated Learningby Christophe Roux, Max Zimmer, Sebastian PokuttaFirst submitted to…
Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge Distillationby Hyunjune Shin, Dong-Wan ChoiFirst submitted to…
GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creationby Ayan Banerjee, Sanket…
Knowledge Distillation Based on Transformed Teacher Matchingby Kaixiang Zheng, En-Hui YangFirst submitted to arxiv on:…
FedD2S: Personalized Data-Free Federated Knowledge Distillationby Kawa Atapour, S. Jamal Seyedmohammadi, Jamshid Abouei, Arash Mohammadi,…
Incremental Sequence Labeling: A Tale of Two Shiftsby Shengjie Qiu, Junhao Zheng, Zhen Liu, Yicheng…