RICA replaces ICA's global generative model with local Riemannian geometry, introducing a disentanglement tensor based on the Hessian of the log-likelihood and Ricci curvature to measure pointwise disentanglement, which recovers sources across manifolds in controlled tests.
Disentangled representation learning.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):9677–9696
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it