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
Heterogeneous Contrastive Learning for Foundation Models and Beyond
Lecheng Zheng
, Baoyu Jing
, Zihao Li
,
Hanghang Tong
,
Jingrui He
Siebel School of Computing and Data Science
National Center for Supercomputing Applications (NCSA)
School of Information Sciences
Informatics
Research output
:
Chapter in Book/Report/Conference proceeding
›
Conference contribution
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Heterogeneous Contrastive Learning for Foundation Models and Beyond'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Foundation Models
100%
Contrastive Learning
100%
Supervised Contrastive Learning
22%
Learning-based
11%
Learning Methods
11%
Multiple Domains
11%
Computer Vision
11%
Explosives
11%
Heterogeneous Data
11%
Emergent Paradigm
11%
Natural Language Processing
11%
Artificial Intelligence
11%
Label Information
11%
Big Data Era
11%
Generalization Ability
11%
Task Heterogeneity
11%
Downstream Task
11%
Model Benefits
11%
Big Data Intelligence
11%
Learning Loss
11%
Pre-training Tasks
11%
Earth and Planetary Sciences
Supervised Learning
100%
Computer Vision
50%
Shedding
50%
Big Data
50%
Natural Language Processing
50%
Artificial Intelligence
50%
Natural Language (Computers)
50%
Social Sciences
Learning Method
100%
Natural Language Processing
100%
Artificial Intelligence
100%
Big Data
100%
Psychology
Artificial Intelligence
100%
Big Data
100%
Computer Vision
100%
Computer Science
Contrastive Learning
100%
Self-Supervised Learning
22%
Natural Language Processing
11%
Future Direction
11%
Big Data
11%
Multiple Domain
11%
Heterogeneous Data
11%
Artificial Intelligence
11%
Computer Vision
11%
Neuroscience
Natural Language Processing
100%