activity
20202022
most citedLearning by Minimizing the Sum of Ranked Range

12 citations · 21 across the 5 of their papers we have counts for

collaborators

6 papers

stat.ML20223 cited

Distributionally Robust Survival Analysis: A Novel Fairness Loss Without Demographics

Shu Hu, George H. Chen

We propose a general approach for training survival analysis models that minimizes a worst-case error across all subpopulations that are large enough (occurring with at least a use…

cs.CV2022

Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Faces

Hui Guo, Shu Hu, Xin Wang +2

AI-synthesized faces are visually challenging to discern from real ones. They have been used as profile images for fake social media accounts, which leads to high negative social i…

cs.CV20222 cited

PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems

Shu Hu, Chun-Hao Liu, Jayanta Dutta +3

Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled. To propagate information from the labeled obje…

cs.CV20214 cited

TML-AP: Adversarial Attacks to Top- Multi-Label Learning

Shu Hu, Lipeng Ke, Xin Wang +1

Top- multi-label learning, which returns the top- predicted labels from an input, has many practical applications such as image annotation, document analysis, and web search…

cs.CV2020

Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights

Shu Hu, Yuezun Li, Siwei Lyu

Sophisticated generative adversary network (GAN) models are now able to synthesize highly realistic human faces that are difficult to discern from real ones visually. In this work,…

cs.LG202012 cited

Learning by Minimizing the Sum of Ranked Range

Shu Hu, Yiming Ying, Xin Wang +1

In forming learning objectives, one oftentimes needs to aggregate a set of individual values to a single output. Such cases occur in the aggregate loss, which combines individual l…