most citedFedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space

42 citations · 53 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV202142 cited

FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space

Quande Liu, Cheng Chen, Jing Qin +2

Federated learning allows distributed medical institutions to collaboratively learn a shared prediction model with privacy protection. While at clinical deployment, the models trai…

eess.SY20214 cited

Computation Resource Allocation Solution in Recommender Systems

Xun Yang, Yunli Wang, Cheng Chen +4

Recommender systems rely heavily on increasing computation resources to improve their business goal. By deploying computation-intensive models and algorithms, these systems are abl…

cs.CV20217 cited

MITNet: GAN Enhanced Magnetic Induction Tomography Based on Complex CNN

Zuohui Chen, Qing Yuan, Xujie Song +5

Magnetic induction tomography (MIT) is an efficient solution for long-term brain disease monitoring, which focuses on reconstructing bio-impedance distribution inside the human bra…

cs.LG2020

Neural Rate Control for Video Encoding using Imitation Learning

Hongzi Mao, Chenjie Gu, Miaosen Wang +9

In modern video encoders, rate control is a critical component and has been heavily engineered. It decides how many bits to spend to encode each frame, in order to optimize the rat…

math.OC2020

Efficient Projection-Free Algorithms for Saddle Point Problems

Cheng Chen, Luo Luo, Weinan Zhang +1

The Frank-Wolfe algorithm is a classic method for constrained optimization problems. It has recently been popular in many machine learning applications because its projection-free…

cs.LG2020

Revisiting Co-Occurring Directions: Sharper Analysis and Efficient Algorithm for Sparse Matrices

Luo Luo, Cheng Chen, Guangzeng Xie +1

We study the streaming model for approximate matrix multiplication (AMM). We are interested in the scenario that the algorithm can only take one pass over the data with limited mem…