The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders
Researchers have identified a consistent geometric structure, termed the "cross-architecture substrate," within modern vision encoders, regardless of their specific training objective or domain. This substrate, a 16-dimensional object, remains stable across diverse visual domains and survives calibration tests. The findings suggest a fundamental invariant in how these networks process visual information, leading to practical applications in areas like model transferability and domain detection. AI
IMPACT Reveals a fundamental invariant in vision model representations, enabling new methods for model analysis and transfer.