Off-the-shelf vision-language models can auto-label training data well enough that lightweight object detectors trained on those labels are competitive with human-labeled training on VOC and COCO.
Weakly supervised deep detection networks
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
-
Auto-Labeling Data for Object Detection
Off-the-shelf vision-language models can auto-label training data well enough that lightweight object detectors trained on those labels are competitive with human-labeled training on VOC and COCO.