Skip to main navigation
Skip to search
Skip to main content
Hong Kong Baptist University Home
Help & FAQ
Link opens in a new tab
Search content at Hong Kong Baptist University
Home
Scholars
Departments / Units
Research Output
Projects / Grants
Prizes / Awards
Activities
Press/Media
Student theses
Datasets
Key Point Sensitive Loss for Long-Tailed Visual Recognition
Mengke Li
,
Yiu-Ming Cheung
*
, Zhikai Hu
*
Corresponding author for this work
Department of Computer Science
Research output
:
Contribution to journal
›
Journal article
›
peer-review
36
Citations (Scopus)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Key Point Sensitive Loss for Long-Tailed Visual Recognition'. Together they form a unique fingerprint.
Sort by:
Weight
Alphabetically
Keyphrases
Classification Model
100%
Negative Signal
100%
Long Tail
100%
Long-tailed Recognition
100%
Gradient Adjustment
100%
Gradient Analysis
50%
Classification Accuracy
50%
Generalization Performance
50%
Positive Samples
50%
Generalization Ability
50%
Optimization Strategy
50%
Loss Function
50%
Large Margin
50%
Negative Samples
50%
Poor Generalization
50%
Rebalance
50%
Competent Performance
50%
Adjustment Strategy
50%
Overall Classification Accuracy
50%
Computer Science
Classification Accuracy
100%
Classification Models
100%
Long-Tailed Visual Recognition
100%
Generalization Performance
50%
Optimization Strategy
50%
Engineering
Classification Accuracy
100%
Conducted Experiment
50%
Optimization Strategy
50%
Loss Function
50%
Mathematics
Loss Function
100%
Distributed Data
100%