Slim-Net uses stacked Slim Modules of depthwise separable convolutions to predict face attributes on CelebA at 91.24% accuracy with at least 25 times fewer parameters than comparable models.
Going deeper with convolutions
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
-
Slim-CNN: A Light-Weight CNN for Face Attribute Prediction
Slim-Net uses stacked Slim Modules of depthwise separable convolutions to predict face attributes on CelebA at 91.24% accuracy with at least 25 times fewer parameters than comparable models.