SOTAVerified

Unsupervised Domain Adaptation

Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.

Source: Domain-Specific Batch Normalization for Unsupervised Domain Adaptation

Papers

Showing 1–10 of 1951 papers

TitleStatusHype
CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble FusionCode0
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud RecognitionCode0
Unlocking Constraints: Source-Free Occlusion-Aware Seamless SegmentationCode0
Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments—0
MUDAS: Mote-scale Unsupervised Domain Adaptation in Multi-label Sound Classification—0
Customizing Speech Recognition Model with Large Language Model Feedback—0
Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object DetectorCode1
Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image SegmentationCode0
Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI—0
MSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR—0
Show:102550
← PrevPage 1 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CORE-ReID V2mAP57.99—Unverified
2CORE-ReID V2 TinymAP55.14—Unverified
3DMDUmAP53.97—Unverified
4UDARmAP52.9—Unverified
5MGR-GCLmAP47.59—Unverified
6PMLmAP46—Unverified
7PALmAP45.14—Unverified
8MLmAP45—Unverified
9VDAFR-143.69—Unverified
10CSP+FCDmAP42.7—Unverified