A tiny-object detector with high-to-low level feature fusion and a sigmoid-weighted L1/L2 loss reports +1.3 AP on AI-TOD, but the loss gradient claims are contradicted by the paper's own equations.
Cascade r-cnn: Delving into high quality object detection, in: CVPR
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny Objects
A tiny-object detector with high-to-low level feature fusion and a sigmoid-weighted L1/L2 loss reports +1.3 AP on AI-TOD, but the loss gradient claims are contradicted by the paper's own equations.