activity
20192025
most citedUnderstanding and Utilizing Deep Neural Networks Trained with Noisy Labels

96 citations · 355 across the 26 of their papers we have counts for

collaborators
Showing 2020Show all

5 papers · 1 filter

cs.LG2020★ 14 cited

Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise

Pengfei Chen, Junjie Ye, Guangyong Chen +2

Supervised learning under label noise has seen numerous advances recently, while existing theoretical findings and empirical results broadly build up on the class-conditional noise…

cs.LG2020★ 10 cited

Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels

Pengfei Chen, Junjie Ye, Guangyong Chen +2

For multi-class classification under class-conditional label noise, we prove that the accuracy metric itself can be robust. We concretize this finding's inspiration in two essentia…

cs.CV2020

A Rotation-Invariant Framework for Deep Point Cloud Analysis

Xianzhi Li, Ruihui Li, Guangyong Chen +3

Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to ar…

cs.MA2020★ 26 cited

Q-value Path Decomposition for Deep Multiagent Reinforcement Learning

Yaodong Yang, Jianye Hao, Guangyong Chen +5

Recently, deep multiagent reinforcement learning (MARL) has become a highly active research area as many real-world problems can be inherently viewed as multiagent systems. A parti…

cs.MA2020

Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning

Yaodong Yang, Jianye Hao, Ben Liao +4

In many real-world tasks, multiple agents must learn to coordinate with each other given their private observations and limited communication ability. Deep multiagent reinforcement…