HyperAIHyperAI超神经
首页算力平台文档资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Image Classification On Resisc45

评估指标

Top 1 Accuracy

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
ResNet5096.83In-domain representation learning for remote sensing
LWGANet L296.17LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks
DecoupleNet D295.87DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks-
LWGANet L195.70LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks
SEER (RegNet10B)95.61Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
LWGANet L095.49LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks
AGOS94.91All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification
SwAV (ResNet50-w5)94.73Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
DINO (DeiT-B/16)93.97Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
LSENet93.49Local semantic enhanced convnet for aerial scene recognition-
MoCo-v3 (ViT-B/16)93.35Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
CLIP (ViT-B/16)92.7Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
BYOL (ResNet200-w2)92.53--
DeiT-B/1692.48Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
SimCLR-v2 (ResNet152-w3 + SK)89.77Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
ResNet50 (ImageNet-supervised)88.56Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
MIDC-Net87.99A multiple-instance densely-connected ConvNet for aerial scene classification-
MoCo-v2 (ResNet50)85.4Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
SAG-ViT-SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers
0 of 19 row(s) selected.
Image Classification On Resisc45 | SOTA | HyperAI超神经