AI RESEARCH
Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection
arXiv CS.CL
•
ArXi:2606.00684v1 Announce Type: cross We address the problem of out-of-distribution (OOD) detection for target observations embedded in a subspace of the high dimensional data space. Using continuous normalizing flows (CNFs), we propose a Lagrangian sub-flow (LSF) framework designed to isolate and estimate the density for the relevant components in the representation and using the remaining components as context.