A 9x9 grid representation of DTI tract FA values, encoded by a beta-TCVAE with spatial broadcast decoder, yields improved downstream sex classification F1 and higher MIG than a 3D VAE baseline.
Deep metric learning using triplet network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Interpretable Representation Learning Approach for Diffusion Tensor Imaging
A 9x9 grid representation of DTI tract FA values, encoded by a beta-TCVAE with spatial broadcast decoder, yields improved downstream sex classification F1 and higher MIG than a 3D VAE baseline.