GATA2Floor applies multi-head GATv2 on facade graphs to predict building floor counts and softly assign elements to latent floors, with a label-free version using self-supervised features.
Decoupled weight decay regularization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
APRIL augments neural network loss with auxiliary physical redundancy terms to reshape the optimization landscape while preserving the true minimum, yielding up to 10x better accuracy in noise-free gravitational wave parameter estimation for chirp mass, total mass, and mass ratio.
citing papers explorer
-
GATA2Floor: Graph attention for floor counting in street-view facades
GATA2Floor applies multi-head GATv2 on facade graphs to predict building floor counts and softly assign elements to latent floors, with a label-free version using self-supervised features.
-
APRIL: Auxiliary Physically-Redundant Information in Loss -- A physics-informed framework for parameter estimation with a gravitational-wave case study
APRIL augments neural network loss with auxiliary physical redundancy terms to reshape the optimization landscape while preserving the true minimum, yielding up to 10x better accuracy in noise-free gravitational wave parameter estimation for chirp mass, total mass, and mass ratio.