λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.
Latent space translation via inverse relative projection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
Learned anchors as semantic prototypes combined with whitened inner products improve relative representations, enabling nearly lossless zero-shot communication between heterogeneous neural models on vision and language tasks.
citing papers explorer
-
$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.
-
Improving Relative Representations with Learned Anchors and Whitened Inner Products
Learned anchors as semantic prototypes combined with whitened inner products improve relative representations, enabling nearly lossless zero-shot communication between heterogeneous neural models on vision and language tasks.