FMG-Det adds an offline SAM plus CLIP box-correction stage and a learned noisy/corrected box interpolation to MIL-based detection, sharply reducing accuracy loss under heavy bounding-box noise on VOC and COCO, including few-shot settings.
Since these splits are fully aligned with prior works, we do not exhaustively run all baseline models as all of the results that we present are directly comparable
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
FMG-Det: Foundation Model Guided Robust Object Detection
FMG-Det adds an offline SAM plus CLIP box-correction stage and a learned noisy/corrected box interpolation to MIL-based detection, sharply reducing accuracy loss under heavy bounding-box noise on VOC and COCO, including few-shot settings.