43 citations · 211 across the 27 of their papers we have counts for
Showing cs.CVShow all
3 papers · 1 filter
cs.CV2021
Distilling Holistic Knowledge with Graph Neural Networks
Sheng Zhou, Yucheng Wang, Defang Chen +4
Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network.Existing KD methods have mainly consi…
cs.CV2021★ 5 cited
Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation
Ning Ma, Jiajun Bu, Lixian Lu +4
Domain Adaptation has been widely used to deal with the distribution shift in vision, language, multimedia etc. Most domain adaptation methods learn domain-invariant features with…
cs.CV2021★ 22 cited
Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
Ning Ma, Jiajun Bu, Zhen Zhang +1
Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not al…