RTSM improves SFDA-OD by 1.7-18.3 AP50 across methods and detectors, and ten sparse-label feedback plugins give only limited method-dependent gains over it.
arXiv preprint arXiv:2205.10711 (2022) 18
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Simple Supervision Is Hard to Beat: A Bitter Lesson from Sparse Target Labels in Domain-Adaptive Object Detection
RTSM improves SFDA-OD by 1.7-18.3 AP50 across methods and detectors, and ten sparse-label feedback plugins give only limited method-dependent gains over it.