Unsupervised Domain Adaptation On Visda2017

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
FFTAT	93.8	Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation
RCL	93.2	Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning
TransAdapter	91.2	TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation
SAMB	90.41	Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation
PDA (CLIP, ViT-B/16)	89.7	Prompt-based Distribution Alignment for Unsupervised Domain Adaptation
SFDA2++	89.6	SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
PMTrans	88.8	Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective
SSRT-B (ours)	88.76	Safe Self-Refinement for Transformer-based Domain Adaptation
SFDA2	88.1	SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
PDA (CLIP, ResNet-101)	86.4	Prompt-based Distribution Alignment for Unsupervised Domain Adaptation
Implicit Alignment (with MDD)	75.8	Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation
DeepJDOT	66.9	DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
DisClusterDA	-	Unsupervised Domain Adaptation via Distilled Discriminative Clustering

0 of 13 row(s) selected.

Unsupervised Domain Adaptation On Visda2017 | SOTA | HyperAI