VG-DETR combines a mean-teacher detector with DINOv2-guided pseudo-label mining and dual-level feature alignment, reporting 77.5% mAP on xView to DOTA and 70.6% on HRRSD to SSDD.
Style-hallucinated dual consistency learning for domain generalized semantic segmenta- tion,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection
VG-DETR combines a mean-teacher detector with DINOv2-guided pseudo-label mining and dual-level feature alignment, reporting 77.5% mAP on xView to DOTA and 70.6% on HRRSD to SSDD.