HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Unsupervised Domain Adaptation On Sim10K To 3

Métriques

mAP@0.5

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
mAP@0.5
Paper TitleRepository
SADA (ResNet50-FPN, 1024px)71.8Align and Distill: Unifying and Improving Domain Adaptive Object Detection
ILLUME53.1To miss-attend is to misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors
MRT62.0Masked Retraining Teacher-Student Framework for Domain Adaptive Object Detection
ALDI-YOLO (1024px)75.0Align and Distill: Unifying and Improving Domain Adaptive Object Detection
UMT (ResNet50-FPN, 1024px)58.7Align and Distill: Unifying and Improving Domain Adaptive Object Detection
MIC (ResNet50-FPN, 1024px)73.1Align and Distill: Unifying and Improving Domain Adaptive Object Detection
MILA57.4MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection
ViSGA52.1Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection
AT (ResNet50-FPN, 1024px)72.0Align and Distill: Unifying and Improving Domain Adaptive Object Detection
AWADA54.1AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection-
PT (ResNet50-FPN, 1024px)70.6Align and Distill: Unifying and Improving Domain Adaptive Object Detection
ALDI++ (ResNet50-FPN, 1024px)78.2Align and Distill: Unifying and Improving Domain Adaptive Object Detection
0 of 12 row(s) selected.