Object Detection In Aerial Images On Dota 1

评估指标

mAP

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
Strip R-CNN*82.75%Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection
MoCaE82.62%MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Strip R-CNN82.28%Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection
Oriented-DETR82.26%Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation
STD+HiViT-B82.24%Spatial Transform Decoupling for Oriented Object Detection
CDLA-HOP82.02%Category-Aware Dynamic Label Assignment with High-Quality Oriented Proposal-
LSKNet-S*81.85%LSKNet: A Foundation Lightweight Backbone for Remote Sensing
ARC81.77%Adaptive Rotated Convolution for Rotated Object Detection
MAE+MTP(ViT-L+RVSA)81.66%MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
LSKNet-S81.64%LSKNet: A Foundation Lightweight Backbone for Remote Sensing
LSKNet-T81.37%LSKNet: A Foundation Lightweight Backbone for Remote Sensing
ViTAE-B + RVSA-ORCN81.24%Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model
ViT-B + RVSA-ORCN81.01%Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model
Oriented RCNN80.87%Oriented R-CNN for Object Detection
IMP+MTP(InternImage-XL)80.77%MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
PP-YOLOE-R-x80.73%PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector
MAE+MTP(ViT-B+RVSA)80.67%MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
KLD+R3Det80.63%Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
DEA-Net80.37%Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images
GWD+R3Det80.23%Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
0 of 58 row(s) selected.