Skip to main navigation
Skip to search
Skip to main content
Hong Kong Baptist University Home
Help & FAQ
Home
Scholars
Departments / Units
Research Output
Projects / Grants
Prizes / Awards
Activities
Press/Media
Student theses
Datasets
Search by expertise, name or affiliation
Long-Tailed Visual Recognition via Gaussian Clouded Logit Adjustment
Mengke Li
,
Yiu Ming Cheung
*
, Yang Lu
*
Corresponding author for this work
Department of Computer Science
Research output
:
Chapter in book/report/conference proceeding
›
Conference proceeding
›
peer-review
122
Citations (Scopus)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Long-Tailed Visual Recognition via Gaussian Clouded Logit Adjustment'. Together they form a unique fingerprint.
Sort by:
Weight
Alphabetically
Keyphrases
Balanced Data
66%
Benchmark Dataset
33%
Class-based
33%
Cloud Size
100%
Cross-entropy
66%
Deep Neural Network
33%
Effective number
33%
Embedding Space
66%
Gaussian Perturbation
33%
Logit
66%
Logit Adjustment
100%
Long-tail Problem
33%
Long-tailed Data
100%
Long-tailed Recognition
100%
Sampling Strategy
33%
Softmax
100%
Source Code
33%
Spatial Distribution
33%
Superior Performance
33%
Vanilla
33%
Computer Science
Biggest Challenge
50%
Deep Neural Network
50%
Embedding Space
100%
Long-Tailed Visual Recognition
100%
Spatial Distribution
50%
Superior Performance
50%
Mathematics
Balanced Data
66%
Deep Neural Network
33%
Gaussian Distribution
100%
Spatial Distribution
33%
Engineering
Deep Neural Network
33%
Gaussians
100%
Spatial Distribution
33%