1 citations · 1 across the 4 of their papers we have counts for
5 papers
Unified Response Geometry for Structured Pruning
Kaixiang Shu
Structured pruning is commonly formulated as ranking individual channels, although channel responses can be complementary or cancel through downstream mixing. Motivated by these re…
From Preimage Search To Source-Grounded Feature Inversion
Kaixiang Shu
Interpreting a neural network requires understanding what its internal features extract from a particular input. Feature inversion seeks to express a selected feature in the input…
Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers
Kaixiang Shu
How do CNN channels combine scene information into a class-specific response? We develop an input-conditioned adjoint inversion framework that renders individual channels and their…
CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models
Weining Fu, Kai Shu, Kui Xu +1
Cryo-electron microscopy (cryo-EM) has revolutionized structural biology by enabling near-atomic-level visualization of biomolecular assemblies. However, the exponential growth in…
Spatial Information Bottleneck for Interpretable Visual Recognition
Kaixiang Shu, Kai Meng, Junqin Luo
Deep neural networks typically learn spatially entangled representations that conflate discriminative foreground features with spurious background correlations, thereby undermining…