2022
DOI: 10.1109/jstars.2022.3211994
|View full text |Cite
|
Sign up to set email alerts
|

CC-SSL: A Self-Supervised Learning Framework for Crop Classification With Few Labeled Samples

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

1
0
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(1 citation statement)
references
References 36 publications
1
0
0
Order By: Relevance
“…In study area IV, Cropformer obtained AA of 81.52%, which was very close to the OA (84.39%) obtained in this region, while in study areas II and III it obtained AA of 64.81% and 61.23%, respectively, which was more than 20% different from the OA (86.32%, 85.70%) obtained, and this difference was more pronounced in RF (37%, 25%). This was due to the extremely unbalanced distribution of samples in study area II and III, where the sample size of maize was more than half of the total sample size, causing the AA to be insignificant, which is consistent with the findings of (Wang et al, 2022). Sample imbalance can bias the classification results toward the more numerous categories.…”
Section: Full-season Crop Classificationsupporting
confidence: 74%
“…In study area IV, Cropformer obtained AA of 81.52%, which was very close to the OA (84.39%) obtained in this region, while in study areas II and III it obtained AA of 64.81% and 61.23%, respectively, which was more than 20% different from the OA (86.32%, 85.70%) obtained, and this difference was more pronounced in RF (37%, 25%). This was due to the extremely unbalanced distribution of samples in study area II and III, where the sample size of maize was more than half of the total sample size, causing the AA to be insignificant, which is consistent with the findings of (Wang et al, 2022). Sample imbalance can bias the classification results toward the more numerous categories.…”
Section: Full-season Crop Classificationsupporting
confidence: 74%