Sep 2026· IEEE Transactions on Neural Networks and Learning Systems· Vol PP· 0 citations
Medicine
TL;DR
MoLiegroup is introduced, a framework that embeds multiple Lie-group priors as specialized kernel experts and adaptively fuses them via a geometry-aware gating mechanism to learn equivariance-inspired geometric features and supplies a practical, architecture-agnostic geometric inductive bias that improves expressivity and generalization across a wide range of vision tasks.
Abstract
Deep visual models typically achieve robustness to geometric transformations through extensive data augmentation or increased model capacity, yet these empirical strategies do not guarantee explicitly equivariant or structurally constrained representations. While group-equivariant CNNs provide principled mechanisms for embedding symmetry, existing methods are commonly specialized to individual groups or struggle to balance expressivity when facing compound transformations. To address these limitations, we introduce MoLiegroup, a framework that embeds multiple Lie-group priors as specialized kernel experts and adaptively fuses them via a geometry-aware gating mechanism to learn equivariance-inspired geometric features. Each expert is parameterized from a spectral and representation-theoretic perspective: angular harmonic expansions encode rotation components, spatial harmonics model translations, and log-radial decompositions cover scale effects. An input-dependent router produces expert weights, and a load-balancing regularizer encourages uniform expert utilization, enabling the operator to interpolate between rotation-, translation-, and scale-equivariant responses at each spatial location. We validate MoLiegroup on both discriminative and generative tasks. These findings indicate that MoLiegroup supplies a practical, architecture-agnostic geometric inductive bias that improves expressivity and generalization across a wide range of vision tasks.
Flow-Based Distribution Matching is introduced, a non-adversarial framework that learns this reference-directed geometry through spherical conditional velocity regression that achieves performance nearly on par with DM and remains competitive with existing SSL methods.
This tutorial provides a comprehensive introduction to rotational equivariance, starting from the physical and geometric intuition behind coordinate independence and building up the necessary machinery from geometric deep learning, group theory, and representation theory.
Aether is introduced, a simple plug-in method that applies diffusion-style random perturbations in the embedding space via controlled alpha-mixing, specifically designed to provide isotropic regularization that remains semantically consistent.
Hyesong Choi, Daeun Kim, Song Park et al.· European Conference on Compu...· 0 citations
This work introduces a Nested Inductive Bias framework that utilizes a two-stage diffeomorphic composition to formally pull back non-Euclidean target geometries onto the SPD manifold, and proposes the Rational Conformal Metric (RCM), designed to establish state-of-the-art geometric robustness against outliers by boundi...
KGFT is proposed, a lightweight module that derives a geometric guidance matrix from the kernel Gram matrix and uses it to transform the covariance structure of feature representations, validating the generality and effectiveness of kernel-guided dual-manifold representation learning.
Wencong Zhang, Yue Zhang, Meiyan Huang et al.· 0 citations
It is concluded that future industrial deployment on edge-computing platforms will rely on a synergy between lightweight network architectures and multi-sensor fusion and self-supervised frameworks.