A post-processing GCN multiplies detector confidence scores by a learned category-correction vector, trained from COCO co-occurrence statistics, and is claimed to improve mAP by 1-5 points on standard detectors.
For one reason, humans can recognize an object not only by knowledge of the object itself, but also by its surrounding objects
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
OD-GCN: Object Detection Boosted by Knowledge GCN
A post-processing GCN multiplies detector confidence scores by a learned category-correction vector, trained from COCO co-occurrence statistics, and is claimed to improve mAP by 1-5 points on standard detectors.