← Search

Hengjie Song

2 accepted papers

2024

Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation

ICLR 2024poster

The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for some period) due to the potential high cost of model adapta…

2021

Unsupervised Real-World Image Super Resolution via Domain-Distance Aware Training

CVPR 2021poster

These days, unsupervised super-resolution (SR) is soaring due to its practical and promising potential in real scenarios. The philosophy of off-the-shelf approaches lies in the augmentation of unpaired data, i.e. first generating synthetic low-resolution (LR) images Y^g corresponding to real-world h…

Cited by 170PDFcodeScholar