AVDNet adds ConvRes residual blocks and larger output maps to a one-stage detector for small aerial vehicles, reports mAP gains on VEDAI, DLR-3K, DOTA and new ABD dataset, and introduces RFAV visualization.
For our experiments, we have divided each image (total of 20 images) into 16 parts to gen- erate 320 images
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AVDNet: A Small-Sized Vehicle Detection Network for Aerial Visual Data
AVDNet adds ConvRes residual blocks and larger output maps to a one-stage detector for small aerial vehicles, reports mAP gains on VEDAI, DLR-3K, DOTA and new ABD dataset, and introduces RFAV visualization.