Study on Multi-label Image Classification Based on Sample Distribution Loss
Different from the data distribution in general image classification scenarios,in the scenario of multi label image classification,the sample number distribution among different label categories is unbalanced,and a small number of head categories often account for the majority of sample size.However...
Main Author: | ZHU Xu-dong, XIONG Yun |
---|---|
Format: | Article |
Language: | zho |
Published: |
Editorial office of Computer Science
2022-06-01
|
Series: | Jisuanji kexue |
Subjects: | |
Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-6-210.pdf |
Similar Items
-
Improving Neural Network-Based Multi-Label Classification With Pattern Loss Penalties
by: Worawith Sangkatip, et al.
Published: (2024-01-01) -
Exploiting Associations between Class Labels in Multi-label Classification
by: Z. Mirzamomen, et al.
Published: (2019-03-01) -
From Scores to Predictions in Multi-Label Classification: Neural Thresholding Strategies
by: Karol Draszawka, et al.
Published: (2023-06-01) -
Robust Multi-Label Classification with Enhanced Global and Local Label Correlation
by: Tianna Zhao, et al.
Published: (2022-05-01) -
Multi-Label Classification With Hyperdimensional Representations
by: Rishikanth Chandrasekaran, et al.
Published: (2023-01-01)