A Geometric View of SRC: Learning Representations for Stable Residual Inference 事件

A Geometric View of SRC: Learning Representations for Stable Residual Inference arXiv:2605.29673v1 Announce Type: cross Abstract: Reconstruction-based inference assigns a class by comparing class-wise reconstruction residuals; Sparse Representation Classification (SRC) is a canonical instance whose reliability depends on the geometry of the learned representation. We adopt a strict training-inference separation: SRC is used only as a fixed test-time rule and is never differentiated, unrolled, o