SOURCE-LINKED INTELLIGENCE

QINA: Quantum-Inspired Nonlinear Adapters for Pretrained Vision Models

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Adapting large pretrained vision models under limited data and frozen-backbone constraints remains a central challenge in transfer learning. While lightweight adapters and parameter-efficient fine-tuning methods are widely adopted, most rely on generic multilayer perceptrons or low-rank linear updates, offering limited control over the spectral and geometric structure of feature transformations. We investigate whether structured nonlinear feature lifting can improve representational alignment in frozen regimes. We introduce Quantum-Inspired Nonlinear Adapters (QINA), compact modules that perfo

Read original source ↗ Open in workspace

recordType

paper

region

Global