Scene Classification On Uc Merced Land Use

Accuracy (%)

Results

Performance results of various models on this benchmark

		Paper Title
µ2Net+ (ViT-L/16)	100	A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems
AGOS	99.88	All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification
LSE-Net	99.78	Local semantic enhanced convnet for aerial scene recognition
ResNet50	99.61	In-domain representation learning for remote sensing
MSMatch	98.33	MSMatch: Semi-Supervised Multispectral Scene Classification with Few Labels
MIDC-Net	97.40	A multiple-instance densely-connected ConvNet for aerial scene classification

0 of 6 row(s) selected.