SOTAVerified

Source Free Object Detection

Source-Free Object Detection (SFOD) is a domain adaptation challenge in which only the pretrained source model weights are available during adaptation, with no access to the source data. The model must adapt solely using unlabeled samples from the target domain

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–17 of 17 papers

TitleStatusHype
Context Aware Grounded Teacher for Source Free Object DetectionCode0
Dynamic Retraining-Updating Mean Teacher for Source-Free Object DetectionCode1
Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label DistillationCode0
Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance InsightsCode1
Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive DistillationCode0
Source-free Domain Adaptive Object Detection in Remote Sensing Images—0
CLIP-Guided Source-Free Object Detection in Aerial ImagesCode1
Periodically Exchange Teacher-Student for Source-Free Object DetectionCode1
Exploiting Low-confidence Pseudo-labels for Source-free Object Detection—0
Adversarial Alignment for Source Free Object Detection—0
Instance Relation Graph Guided Source-Free Domain Adaptive Object DetectionCode1
Source-Free Object Detection by Learning To Overlook Domain StyleCode1
Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source DataCode1
Exploring Sequence Feature Alignment for Domain Adaptive Detection TransformersCode1
A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data—0
Unbiased Mean Teacher for Cross-domain Object DetectionCode1
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultsCode1
Show:102550

No leaderboard results yet.