Foveated resampling retains 92% of full-size foveal recall at 128x128 while uniform downsampling retains only 50%, giving a 4x speedup on a Jetson TX2.
In: NIPS-W (2017), accessed: 2018-10-20
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Foveated image processing for faster object detection and recognition in embedded systems using deep convolutional neural networks
Foveated resampling retains 92% of full-size foveal recall at 128x128 while uniform downsampling retains only 50%, giving a 4x speedup on a Jetson TX2.