A lighter CNN combining Seesaw blocks and squeeze-and-excitation achieves near-state-of-the-art face verification accuracy at reduced cost.
Title resolution pending
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
-
SeesawFaceNets: sparse and robust face verification model for mobile platform
A lighter CNN combining Seesaw blocks and squeeze-and-excitation achieves near-state-of-the-art face verification accuracy at reduced cost.