Hongxin Wei | DeepAI

AI Chat

Featured Co-authors

Chi Zhang
179 publications
Gang Niu
93 publications
Hao Cheng
85 publications
Wei Feng
78 publications
Bo An
62 publications
Yixuan Li
57 publications
Jinfeng Yi
54 publications
Songcan Chen
48 publications
Xiangyu Chen
41 publications
Lei Feng
38 publications
Yunfei Chen
26 publications

∙ 06/03/2023

DOS: Diverse Outlier Sampling for Out-of-Distribution Detection

Modern neural networks are known to give overconfident prediction for ou...

0 Wenyu Jiang, et al. ∙

∙ 03/27/2023

On the Importance of Feature Separability in Predicting Out-Of-Distribution Error

Estimating the generalization performance is practically challenging on ...

0 Renchunzi Xie, et al. ∙

∙ 03/18/2023

CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning

Partial-label learning (PLL) is an important weakly supervised learning ...

0 Shiyu Tian, et al. ∙

∙ 12/08/2022

Logit Clipping for Robust Learning against Label Noise

In the presence of noisy labels, designing robust loss functions is crit...

0 Hongxin Wei, et al. ∙

∙ 06/17/2022

Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets

Deep neural networks usually perform poorly when the training dataset su...

0 Hongxin Wei, et al. ∙

∙ 05/19/2022

Mitigating Neural Network Overconfidence with Logit Normalization

Detecting out-of-distribution inputs is critical for safe deployment of ...

0 Hongxin Wei, et al. ∙

∙ 01/31/2022

Can Adversarial Training Be Manipulated By Non-Robust Features?

Adversarial training, originally designed to resist test-time adversaria...

0 Lue Tao, et al. ∙

∙ 01/16/2022

GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation

This paper studies weakly supervised domain adaptation(WSDA) problem, wh...

0 Renchunzi Xie, et al. ∙

∙ 06/21/2021

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise

Learning with noisy labels is a practically challenging problem in weakl...

6 Hongxin Wei, et al. ∙

∙ 12/23/2020

Commission Fee is not Enough: A Hierarchical Reinforced Framework for Portfolio Management

Portfolio management via reinforcement learning is at the forefront of f...

0 Rundong Wang, et al. ∙

∙ 12/09/2020

MetaInfoNet: Learning Task-Guided Information for Sample Reweighting

Deep neural networks have been shown to easily overfit to biased trainin...

0 Hongxin Wei, et al. ∙

∙ 11/06/2020

5G Embraces Satellites for 6G Ubiquitous IoT: Basic Models for Integrated Satellite Terrestrial Networks

Terrestrial communication networks can provide high-speed and ultra-reli...

0 Xinran Fang, et al. ∙

∙ 05/24/2020

Rethinking Blockchains in the Internet of Things Era from a Wireless Communication Perspective

Due to the rapid development of Internet of Things (IoT), a massive numb...

0 Hongxin Wei, et al. ∙

∙ 03/05/2020

Combating noisy labels by agreement: A joint training method with co-regularization

Deep Learning with noisy labels is a practically challenging problem in ...

0 Hongxin Wei, et al. ∙

∙ 01/06/2020

Creating Efficient Blockchains for the Internet of Things by Coordinated Satellite-Terrestrial Networks

Blockchain has emerged as a promising technology that can guarantee data...

0 Hongxin Wei, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world