12 papers
A Robust Framework for Model Order Selection in Correlated Large-Dimensional CES Noise
Eugénie Terreaux, Emmanuelle Jay, Frédéric Pascal +1
This paper addresses model order selection under large-dimensional, correlated, non-Gaussian noise. Sources are assumed to be embedded in additive Complex Elliptically Symmetric (C…
Backbone-Equated Diffusion OOD via Sparse Internal Snapshots
Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3
Fair comparison between diffusion-based OOD detectors is challenging, as conclusions can vary with backbone choice, corruption parameterization, and test-time budget. We address th…
Radar Detection through Rectified Flow Matching
P. Meena, Y. A. Rouzoumka, J. Pinsolle +3
Radar target detection in the presence of a mixture of non-Gaussian clutter and white thermal noise is a challenging problem. This paper proposes a Rectified Flow Matching-based me…
GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Models
Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3
Diffusion models learn a time-indexed score field that often inherits approximate equivariances (flips, rotations, circular shifts) from in-distribu…
DopplerGLRTNet for Radar Off-Grid Detection
Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3
Off-grid targets whose Doppler (or angle) does not lie on the discrete processing grid can severely degrade classical normalized matched-filter (NMF) detectors: even at high SNR, t…
Support Vector Data Description for Radar Target Detection
Jean Pinsolle, Yadang Alexis Rouzoumka, Chengfang Ren +2
Classical radar detection techniques rely on adaptive detectors that estimate the noise covariance matrix from target-free secondary data. While effective in Gaussian environments,…