Skip to main navigation
Skip to search
Skip to main content
Illinois Experts Home
LOGIN & Help
Home
Profiles
Research units
Research & Scholarship
Datasets
Honors
Press/Media
Activities
Search by expertise, name or affiliation
Enhancing the reliability of out-of-distribution image detection in neural networks
Shiyu Liang, Yixuan Li,
R. Srikant
Electrical and Computer Engineering
Siebel School of Computing and Data Science
Coordinated Science Lab
Office of the Vice Chancellor for Research and Innovation
Research output
:
Contribution to conference
›
Paper
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Enhancing the reliability of out-of-distribution image detection in neural networks'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Neural Network
100%
Image Detection
100%
Effective Method
50%
Small Perturbation
50%
False Positive Rate
50%
Network Architecture
50%
Score Distribution
50%
Softmax
50%
Temperature Scaling
50%
ImageNet
50%
Art Performance
50%
True Positive Rate
50%
Diverse Networks
50%
Large Margin
50%
Network Datasets
50%
CIFAR-10
50%
DenseNet
50%
Pre-trained Networks
50%
Computer Science
Neural Network
100%
Effective Method
50%
Network Architecture
50%
New-State
50%
Art Performance
50%
Baseline Approach
50%
True Positive Rate
50%
False Positive Rate
50%
Trained Neural Network
50%
DenseNet
50%
Engineering
Tasks
100%
Scaling Temperature
100%
Neuroscience
Neural Network
100%